A Mini-Thesis Submitted For Transfer From MPhil To PhD Predicting Student Success With Learning Analytics On Big Data Sets Conditioning And Behavioural Factors

UNIVERSITY OF SOUTHAMPTON
Faculty of Physical Sciences and Engineering
Electronics and Computer Science
A mini-thesis submitted for transfer from
MPhil to PhD
Supervisors: Ed Zaluska (ejz), Dave Millard (dem)
Examiner: Mark Weal (mjw)
Predicting Student Success with
Learning Analytics on Big Data
Sets: Conditioning and Behavioural
Factors
by Adriana Wilde
July 10, 2014

UNIVERSITY OF SOUTHAMPTON
FACULTY OF PHYSICAL SCIENCES AND ENGINEERING
ELECTRONICS AND COMPUTER SCIENCE
Predicting Student Success with Learning Analytics on Big Data Sets:
Conditioning and Behavioural Factors
A mini-thesis submitted for transfer from MPhil to PhD
by Adriana Wilde
ABSTRACT
Advances in computing technologies have a profound impact in many areas of human
concern, especially in education. Teaching and learning are undergoing a (digital) rev-
olution, not only by changing the media and methods of delivery but by facilitating
a conceptual shift from traditional face-to-face instruction towards a learner-centered
paradigm with delivery increasingly becoming tailored to student needs. Educational
institutions of the immediate future have the potential to predict (and even facilitate)
student success by applying learning analytics techniques on the large amount of data
they hold about their learners, which include a number of indicators that measure both
the conditioning (under which students are subjected) and the behavioural factors (what
students do) influencing whether a given student will be successful. More than ever
before, key information about successful student habits and learning context can be
discovered.
Our hypothesis is that collective data can be used to construct a model of success for
Higher Education students, which then can be used to identify students at risk. This
is a complex issue which is receiving increased attention amongst e-learning commu-
nities (of which Massive Open Online Courses are an example), and administrators of
learning management system alike. Smartphones, as sensor-rich, ubiquitous devices, are
expected to become an important source of such data in the imminent future, increasing
significantly the complexity of the problem of devising an accurate predictive model of
success.
This interim thesis presents the relevant issues in predicting student success using learn-
ing analytics approaches by incorporating both conditioning and behavioural factors
with the ultimate goal of informing behavioural change interventions in the context of
learning in Higher Education. It then discusses our work to date and concludes with a
workplan to generate publishable results.

Contents
1 Introduction 1
2 Background and Literature Review 4
2.1 Higher education learners today . . . . . . . . . . . . . . . . . . . . . . . . 4
2.1.1 A digitally-literate generation of students . . . . . . . . . . . . . . 4
2.1.2 Mature students in HE . . . . . . . . . . . . . . . . . . . . . . . . 6
2.1.3 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 6
2.2 Computers and learning . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
2.2.1 Learning Management Systems . . . . . . . . . . . . . . . . . . . . 7
2.2.2 Learning analytics . . . . . . . . . . . . . . . . . . . . . . . . . . . 9
2.2.3 Massive Open Online Courses . . . . . . . . . . . . . . . . . . . . . 10
2.2.4 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 10
2.3 Smart badges and smartphones . . . . . . . . . . . . . . . . . . . . . . . . 10
2.3.1 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 13
2.4 Behaviour sensing and intervention . . . . . . . . . . . . . . . . . . . . . . 14
2.5 Final comments . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 16
3 A research question 18
3.1 What are the measurable factors for the prediction of student academic
success? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18
4 Outcomes of Work to Date 21
4.1 Survey of HE English-speaking students . . . . . . . . . . . . . . . . . . . 21
4.1.1 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
4.1.2 Findings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
4.2 Survey of students from the University of Chile . . . . . . . . . . . . . . . 24
4.2.1 Methodology . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 24
4.2.2 Findings . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 25
4.3 U-Cursos . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
4.3.1 Current status . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 28
4.3.2 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 30
5 Research Plan for Final Thesis 31
5.1 Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
5.2 Research question and research hypotheses . . . . . . . . . . . . . . . . . 32
5.3 Work Packages . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 34
5.4 Contingency research plan . . . . . . . . . . . . . . . . . . . . . . . . . . . 39
5.5 Summary . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 42
ii

CONTENTS iii
6 Conclusions 43
References 45
A Beyond this thesis 56
A.1 How to help students reflect on their behaviour? . . . . . . . . . . . . . . 56
B Predictability of human behaviour 60
C Survey questions 62
D A word cloud of concerns 66
E The U-Cursos experience 68
F U-Campus Screenshots 75
G Chilean University Selection Test 77
H Additional research 81
H.1 Audience response systems (zappers) . . . . . . . . . . . . . . . . . . . . . 81
H.1.1 Own experience with zappers . . . . . . . . . . . . . . . . . . . . . 82
H.2 Privacy . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 84
H.3 Internet of Things . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 87
H.4 Activity Theory . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 87

List of Figures
2.1 Multi-level categorisation model of conceptions of teaching . . . . . . . . . 8
2.2 Smart badges: The Active Badge by Palo Alto Research Centre . . . . . . 11
2.3 Smart badges: The HBM (external and internal appearance) . . . . . . . 11
2.4 Smart badges: The MIT wearable sociometric badge . . . . . . . . . . . . 12
2.5 A smartphone sensing architecture . . . . . . . . . . . . . . . . . . . . . . 13
2.6 Components of digital behaviour interventions using smartphones . . . . 16
4.1 Survey responses from UK students (excluding qualitative data). . . . . . 23
4.2 Survey of University of Chile students: First screen . . . . . . . . . . . . . 25
4.3 Survey responses from students of the University of Chile (excluding qual-
itative data). . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 26
4.4 U-Cursos view . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 27
4.5 Cramped look to the U-Cursos web interface from a smartphone . . . . . 28
4.6 Access graph between 2010 and 2014 for U-Cursos . . . . . . . . . . . . . 29
5.1 Data architecture at the University of Chile. . . . . . . . . . . . . . . . . . 36
D.1 Participants’ answers to the question “Do any of the potential applications
described cause you any concern? Which ones? Why?” . . . . . . . . . . . 66
F.1 U-Campus courses catalogue. . . . . . . . . . . . . . . . . . . . . . . . . . 75
F.2 U-Campus module catalogue for the Computer Science course. . . . . . . 76
G.1 Chilean University Selection Test (PSU) - step one . . . . . . . . . . . . . 77
G.2 PSU - step two . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 78
G.3 PSU - step three . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 79
G.4 PSU - step four . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 80
H.1 A commercial zapper: A TurningPointTMresponse card . . . . . . . . . . . 82
H.2 Zappers in action: Example exam question with student responses . . . . 83
H.3 Zappers in action: Appraising students confidence on their self-assessment
before (left slide) and after (right slide) the solution was discussed in class. 84
iv

List of Tables
3.1 What do students do? . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
4.1 U-Cursos services ranked in ascendent order of popularity amongst users. 30
5.1 Schedule of research work and thesis submission (A Gantt chart) . . . . . 35
5.2 University Selection Tests (PSU) data fields . . . . . . . . . . . . . . . . . 38
5.3 FutureLearn Platform Data Exports . . . . . . . . . . . . . . . . . . . . . 41
A.1 Table of interventions . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 58
v

Chapter 1
Introduction
Recent developments in mobile technologies are characterised by a high integration of
information processing, connectivity and sensing capabilities into everyday objects. It
is now easier than ever to collect, analyse and exchange data about our daily activities:
revolutionising how humans live, work and learn. This is particularly true amongst
higher education students, who already generate a rich “data trail” as they navigate
their way through towards successful completion of their studies.
Traditional learning analytics research focuses on the use of data an educational
institution holds about their students to promptly identify poor performance so that
actions that can be taken to encourage success. Struggling students in particular need to
be directed to be able to complete their courses more successfully (Baepler and Murdoch,
2010), as the failure to do so comes to a great cost, not only to these students but to
their institutions. This is a difficult issue, as measures of success are usually limited
to traditional indicators such as progression and academic performance. For a student,
an educational institution and the wider society, “success” would have to be defined by
retention, level of engagement and contentment as well as achievement of higher marks.
Against this context, Higher Education institutions have, in recent years, devoted
great efforts to support students and encourage them to succeed, by making learning
materials widely available to their students, for example. Furthermore, the greater
affordability of smartphones and the ubiquity of the Internet not only allows students
to access learning materials at any time and any where (although students may well
not see this as the primary benefit of such technologies), but also allows academics to
learn more about student habits and context than ever before. In other words: what do
students actually do and could this information empower them to do better?
One valid approach to understanding how students learn may use technology to
gather data about the conditioning factors for their success as well as the behaviours
they adopt in their student lives. A second step would then use these indicators to
1

Chapter 1 Introduction 2
predict student success in time to perform an intervention on those students identified
as “at risk”. The technology available for collecting activity data is not only becoming
more diverse and powerful but it is also becoming widely available at a decreasing costs,
hence increasing the potential for building “Big Data” collections on which sophisticated
prediction models could be devised.
Students of today have unprecedented access to a breadth of technology, and this
increase in access justify in its own right an study into how to bring pervasive computing
ideas into learning analytics. Pervasive computing is a ‘post-desktop’ computing model
under which, greater processing power, connectivity and sensing are all available at a low
cost, facilitating a widespread adoption of sensor-loaded, powerful, mobile devices. This
active area of research is concerned with context-awareness, i.e. how tailored services
can be offered to users via interconnected computing devices that are sensitive to the
users context as determined by the processing of sensor data. One area of application
of increasing interest is education. However, in this area much of the current interest
tends to focus on the delivery of learning resources to students (Laine and Joy, 2009,
and references therein) and the provision of virtual learning environments rather than
identifying what students do.
The application of pervasive computing in the area of education exploits both the
opportunity of the ubiquity of devices and the increasing interest in new technology
exhibited across the current generation of students. Although there has been a great
amount of research in this direction (Laine and Joy, 2009; Hwang and Tsai, 2011, and
references therein), most of this research has been focused on the use of pervasive tech-
nologies to:
• enrich student learning experiences indoors and/or outdoors with digital augmen-
tation (Rogers et al., 2004, 2005);
• assess students (Cheng et al., 2005);
• increase access to content and annotation capabilities in support of peer-to-peer
learning (Yang, 2006);
• inform the learning activity design taking student context into account (Hwang,
Tsai, and Yang, 2008);
• increase interaction by broadening discourse in the classroom (Anderson and Serra,
2011; Griswold et al., 2004) or by playing mobile learning games (Laine et al.,
2010);
• enable ubiquitous learning in resource-limited settings, and observing the influence
of new tools in the adaptation of learning activities and community rules (Pimmer
et al., 2013);

Chapter 1 Introduction 3
• “deconstruct” everyday experiences into digital environments (Owens, Millard,
and Stanford-Clark, 2009; Dix, 2004).
These examples demonstrate the possibility of applying such technologies in educa-
tion. However, they had not set out to use contextual information in order to predict
or even understand student behaviours. To address this shortcoming, we will consider
context aware computing methods and techniques that have been applied successfully in
the areas of healthcare, assisted living and social networking, and apply them to Higher
Education to complement knowledge gained through traditional educational analytics.
Many researchers have worked on the acquisition of context in general and on the dis-
crimination of human activity in particular, such as dos Santos et al. (2010); Lau (2012);
Bieber and Peter (2008); Huynh and Schiele (2005) and Khattak et al. (2011). Their
findings could be applied in this area of research too, especially as the rapid emergence of
the Internet of Things (IoT) means that the available sensor data will grow exponentially
(Manyika et al., 2011). In my opinion, the application of novel techniques from pervasive
computing into an investigation of student behaviour is worth exploring (Wilde, 2013;
Wilde, Zaluska, and Davis, 2013c,d). Indeed, I am interested in exploring the untapped
possibilities of extending learning analytics in a data-rich environment such as the one
that will be prevalent in the Internet of Things, where all specific activities and general
behaviour of students will leave “fingerprints of data” about them. This data trail af-
fords specific contextual information, capable of analysis for measures of engagement,
collaboration and attainment, thereby enabling the provision of adequate and timely
feedback.
Within this research I have already considered certain aspects related to the study of
behaviour in the population of interest, akin to those in ethnographic methods, with my
specific contribution residing on the disconnect between intentions of privacy as declared
by smartphone users and the actual privacy levels evident in their phone interactions
(Wilde et al., 2013b), which is one of the findings from a survey described in detail later
in this report.
This remainder of this upgrade report is organised as follows: Chapter 2 considers
the characteristics of our learners, explores the state of the art in context-aware tech-
nologies and their existing use in education as well as looking at the predictability of
human behaviour and the type of data that is available in order to infer behaviour.
Chapter 3 examines the research question to be addressed during this research: what
are the measurable factors for the prediction of student academic success?. Chapter 4
presents the research work to date, specifically the design and application of a survey of
Higher Education students (in the UK and in Chile), as well as information discovery
for a suitable dataset to explore these factors (on University of Chile students), which
will be prepared by combining data from the platforms U-Campus and U-Cursos here
described. These chapters lead into a plan for the remaining work, which is detailed in
5. Finally, the conclusions of this upgrade thesis are presented in Chapter 6.

Chapter 2
Background and Literature
Review
The general motivation for this research is assisting higher education students to achieve
success. As they are the subjects of interest, they are more precisely described in Sec-
tion 2.1. Then, I look into the use of digital technologies for learning (in Section 2.2),
both from the educational institutions and their students viewpoints, as well as ways
of using mobile and wearable technologies to learn more about students (Section 2.3).
Section 2.4 reviews existing literature on the identification of human behaviour through
these technologies. Finally, Section 2.5 appraises this review as a foundation for predic-
tion of student success using a characterisation of students from measurable data about
their conditioning and behavioural factors.
2.1 Higher education learners today
To learn about student behaviour, it is useful to start with identifying salient charac-
teristics of the students in higher education today, considering those of the “typical”
student, as well as those pertaining to students that do not fit into that classification.
Specifically, I’ll look into two dimensions: one, being the student levels of efficacy or
even engagement with digital technologies (in sub-section 2.1.1) and another one, the
age group to which the student belongs (sub-section 2.1.2).
2.1.1 A digitally-literate generation of students
Prensky’s term digital natives (Prensky, 2001a) is one amongst many1 used to identify
those born “typically between 1982 and 2003 (standard error of ±2 years)” (Berk, 2009,
1
Terms include: Millennials, Generation Y, Echo Boomers, Trophy Kids, Net Generation, Net Geners,
First Digitals, Dot.com Generation and Nexters (Berk, 2009). Other terms are: cybercitizens, netizens,
4

Chapter 2 Background and Literature Review 5
2010). Members of this group, by this definition, are now 11 to 32 years old, so the ma-
jority of students in higher education today would belong to it. Furthermore, according
to Prensky (2001b), many may even process and interpret information differently (al-
legedly due to the plasticity of the brain). These assertions would imply that what have
been regarded as traditionally effective study habits and behaviours for previous gener-
ations are no longer effective and need to be reviewed to accommodate to the needs of
the current generation of students.
Nevertheless, since only a fraction of the world population access digital technologies
to achieve ‘native’-like fluency in their use, the term “digital natives” is not a fit descrip-
tion (Palfrey and Gasser, 2010), and for this reason (amongst others) it has become less
accepted in the current educational discourse. Education, experience, breadth of use
and self-efficacy are more relevant than age in explaining how people become “digital
natives” (Helsper and Eynon, 2010). As a response, Kennedy et al. (2010) proposed
a different classification based on a study comprising 2096 students in Australian uni-
versities: “power users (14% of sample), ordinary users (27%), irregular users (14%)
and basic users (45%)”. However, rather than a discrete classification, a more useful
typology is a continuum, as individuals are placed along it depending on a number of
factors. Jones and Shao (2011) indicate that various demographic factors affect student
responses to new technologies, such as gender, mode of study (distance or place-based)
and whether the student is a home or international one. A JISC report questions the
validity of certain attributed characteristics of this generation (Nicholas, Rowlands, and
Huntington, 2008). Examples are: a preference for “quick information” and the need
to be constantly connected to the web, now proved to be myths: these traits are not
generational. Whilst Turkle (2008) notes that young people have digital devices always-
on and always-on-them, becoming virtually ‘tethered’, this behaviour is not restricted
to young people. For these reasons, this term has increasingly become replaced by the
term digital residents and its counterpart digital visitors (White et al., 2012).
In any case, we acknowledge that many of our students today are not only engaged
in digital technologies in a daily basis, but in their world there have always been digital
technologies in various forms. Even with the proviso that this behaviour may not be
generalisable “outside of the social class currently wealthy enough to afford such things”
(Turkle, 2008), it is an observable behaviour that is becoming increasingly common as
digital technologies have become more affordable than ever before. This suggests that
in the planning of a study involving higher education students as participants, not only
those in this generation should be considered, but also those outside it, such as mature
students.
homo digitalis, homo sapiens digital, technologically enhanced beings, digital youth and the “yuk/wow”
generation (Hockly, 2011; Dawson, 2010).

2.1.2 Mature students in HE
Ascribing generational traits to today’s learners is somewhat an overgeneralisation. As
Jones and Shao (2011) point out, global empirical evidence indicates that, on the whole,
students do not form a generational cohort but they are “a mixture of groups with var-
ious interests, motives, and behaviours”, not cohering into a single group or generation
of students with common characteristics. In particular, research on higher education
students often focus on the standard age band of students under 21 years of age, not
accounting for mature students (this term is typically used to refer to those who are over
this threshold upon entrance).
Even amongst this group, there are significative differences in behaviour and attain-
ment. Studies have found that older mature students were more likely to study part-time
than full-time, as family and work commitments have been acquired. In fact, 90% of
part-time undergraduate students are 25 years old or over and as many as 67% are over
30 (Smith, 2008).
On this note, Baxter and Hatt (1999) argued that mature students could be disag-
gregated according to age bands seemingly correlating with various levels of academic
success. Therefore, instead of considering standard and mature students solely (under
and over 21 respectively), they introduce the distinction between younger and older
matures, as those over 24 were more likely to progress through into their second year,
despite a longer period time out of education. In general the younger mature learners
were more at risk of leaving the course than older mature students.
However, even this division may well be still a poor generalisation about (mature)
students, as beside their age, there are a myriad of more relevant factors affecting their
experience, such as their route into HE, their background and motivation to study, all are
difficult (if not pointless) to use for a classification of mature learners (Waller, 2006). An
approach that acknowledges the individual characteristics of learners is to be preferred
to those requiring conflating them into a homogeneous group, as conclude by Waller
(2006), requiring educational providers to act on means to identify these characteristics
in order to adopt such an approach.
2.1.3 Summary
The literature reviewed in this area validates the need for individualised support and
feedback, delivered timely and directly to each student, if it is to make an impact.
Another conclusion from this review is that students in higher education today have been
exposed to digital technologies (of which wearable and mobile devices are an example),
suggesting that these can become appropriate channels to facilitate this delivery.

2.2 Computers and learning
A natural consequence of the pervasiveness of digital technologies in recent years is that
they are now almost universally use in teaching and learning (to various degrees). In fact,
coinciding with the advent of the personal computer in the 1970s, the term Computer
Assisted Learning was first coined, alongside Computer Assisted Instruction and similar
others, however, these terms are less commonly used as they are becoming replaced in the
educational discourse by the term e-learning. The former have been used to characterise
the use of computers in education, or more specifically, where digital content is used in
teaching and learning. In contrast, the latter is generally used only when the content is
accessed over the Internet (Derntl, 2005; Hughes, 2007; Jones, 2011; Sun et al., 2008).
2.2.1 Learning Management Systems
Learning Management Systems (LMS), also known as virtual learning environments
(VLE) and course management systems, are excellent examples of the application of
e-learning to support traditional face-to-face instruction. These are systems used in the
context of educational institutions offering technology-enhanced learning or computer-
assisted instruction – BlackboardTMand Moodle are the best-known examples.
Stakeholders may have different objectives for using a LMS. For example, Romero
and Ventura (2010) reviewed 304 studies indicating that students use LMS to person-
alise their learning, reviewing specific material and engaging in relevant discussions as
they prepare for their exams. Lecturers and instructors use them to give and receive
prompt feedback about their instruction, as well as to provide timely support to stu-
dents (e.g. struggling students need additional attention to complete their courses more
successfully (Baepler and Murdoch, 2010), as the failure to do so comes at a great cost,
not only to these students but to their institutions). Administrators use LMS to inform
their allocation of institutional resources, and other decision-making processes (Romero
and Ventura, 2010). These authors argue the need for the integration of educational
data mining tools into the e-learning environment, which can be achieved via LMS.
LMS are being increasingly offered by Higher Education institutions (HEIs), a tech-
nological trend making an impact on these institutions. Another trend is the prolifer-
ation of powerful mobile devices such as smartphones and tablets, from which on-line
resources can be accessed2.
2
These two trends push HEIs to provide LMS access via smartphones in a visually appealing and
accessible way. These are inherent requirements of the mobile experience, which is fundamentally dif-
ferent to the desktop one (Benson and Morgan, 2013). Benson and Morgan present their experiences
migrating an existing LMS (StudySpace) to a mobile development, as a response to these pressures and
the pitfalls identified on the Blackboard MobileTM
app.

It is worth noting that the majority of these systems have a client-server archi-
tecture supporting teacher-centric models of learning (common scenarios have teachers
producing the content while students ‘consume’ it) (Yang, 2006). To put this assertion
in context, pedagogic conceptions of teaching and learning are usually understood in
the literature as falling into one of two categories: teacher-centred (content driven) and
student-centred (learning driven) (Jones, 2011, and references therein). Figure 2.1 shows
these orientations as overarching the main five conceptions of teaching and learning
which act as landmarks alongside a continuum of roles in learning. Deep learning occurs
at the bottom end of the scale, as opposed to shallow learning which occurs at the top
end. When student-centred, computer assisted learning can increase students’ satisfac-
tion and therefore engagement and attainment. It is remarkable that the move towards
learner-centredness in Higher Education coincides with the trends towards personalisa-
tion and user-centredness in Human-Computer Interaction and computing technologies
in general.
Imparting information
Teacher-centred
(content-driven)
Transmitting
structured knowledge
Student-teacher
interaction /
apprenticeship
Facilitating
understanding
Conceptual change
/ intellectual
development
Student-centred
(learning-oriented)
Figure 2.1: Multi-level categorisation model of conceptions of teaching (adapted)
Kember (1997).
The trend towards a widespread use of mobile devices, earlier identified, brings an
increased number of opportunities of effecting the conceptual change from the categori-
sation above, as it has the potential of making the learning more student-centred than

before: it would take placer wherever the student goes, whenever it suits the student
best3. Additional opportunities to reach students to either deliver content or to assess
their learning, are coupled with opportunities for other stakeholders at educational insti-
tutions to gain an insight on student achievement (typically progression and completion)
via learning analytics, as presented in the next subsection.
2.2.2 Learning analytics
As well as facilitating engagement, content delivery and even assessment and feedback,
digital technologies have been increasingly being used for facilitating administrative
tasks and decision-making at educational institutions. In particular, in recent years
HE institutions have begun to use data held about their students for learning analytics
(Barber and Sharkey, 2012; Sharkey, 2011; Bhardwaj and Pal, 2011; Glynn, Sauer, and
Miller, 2003).
Learning analytics (also known as academic analytics and educational data mining),
are widely regarded as the analysis of student records held by the institution as well
as course management system audits, including statistics on online participation and
similar metrics, in order to inform stakeholders decisions in HE institutions. Academic
analytics are considered as useful tools to study scholarly innovations in teaching and
learning (Baepler and Murdoch, 2010). According to these authors, the term academic
analytics was originally coined by the makers of the virtual learning environment (VLE)
BlackboardTM, and it has become widely accepted to describe the actions “that can be
taken with real-time data reporting and with predictive modeling” which in turn helps
to suggest likely outcomes from certain behavioural patterns (Baepler and Murdoch,
2010).
Educational data mining involves processing such data (collected from the VLE
or other sources) through machine learning algorithms, enabling knowledge discovery,
which is “the nontrivial extraction of implicit, previously unknown, and potentially
useful information from data” (Frawley, Piatetsky-Shapiro, and Matheus, 1992). Whilst
data mining does not explain causality, it can discover important correlations which
might still offer interesting insights. When applied to higher education, this might enable
the discovery of positive behaviours, such as for example, whether students posting more
than a certain number of times in an online forum tend to have higher final marks, or
whether attendance at lectures is a defining factor for academic success, or even for any
of its measures such as “retention, progression and completion” (Sarker, 2014).
3
The “anywhere, anytime” maxim driving pervasive computing maxim is also a motivator for the
development of the next generation of e-learning. Rubens, Kaplan, and Okamoto (2014) discuss the
evolution of the field, aligning it to the advent of Web 2.0 and 3.0, central to this paradigm of learning.

2.2.3 Massive Open Online Courses
Developments in these learning digital technologies have facilitated the rise of massive
open online courses (MOOCs)4, where the already difficult issues of assessing and provid-
ing feedback increses dramatically in complexity with classes of up to tens of thousands
of learners (Hyman, 2012). Within this context, a considerable amount of interest has
been devoted very recently to the use of learning analytics too, for example:
• On social factors contibuting to student attrition in MOOCs (Rosé et al., 2014;
Yang et al., 2013);
• On linguistic analysis of forum posts to predict learner motivation and cognitive
engagement levels in MOOCs (Wen, Yang, and Rosé, 2014).
2.2.4 Summary
The literature reviewed in this area evidences the impact of digital technologies in the
provision of support and feedback to learners and other stakeholders of educational
institutions, both in terms of facilitating learning and assessment (as in MOOCs, for
example, but in e-learning in general) as well as in terms of characterising the learners
using learning analytics. In doing so, it is possible to identify the variations amongst
learners to better facilitate the learning experience. An important category of digital
technologies used in education includes portable, light-weight devices, which can be
additionally function as sensor carriers, as presented in the following section.
2.3 Smart badges and smartphones
Until recently, cumbersome sensing equipment (often carried in backpacks) was required,
as shown in a survey of early developments in sensing technologies for wearable comput-
ers (Amft and Lukowicz, 2009). These are now replaced by small, light-weight sensors
which are also capable of becoming embedded within badges and phones, for example.
Smart badges are identity cards with embedded processors, sensors and transmitters.
The concept is not new, in fact the first of these wearable computers was developed
two decades ago, by the Olivetti Research Laboratory (Cambridge) and then further
developed by Xerox PARC: the Active Badge (Want et al., 1992; Weiser, 1999), shown
in Figure 2.2.
More recently, smart badges have been used to study social behaviour, as with
the Hitachi’s Business Microscope (HBM) (Ara et al., 2011; Watanabe, Matsuda, and
Yano, 2013) and with its predecessor, the MIT wearable sociometric badge (Wu et al.,
4
MOOCs are occasionally referred to as “Massively-Open Online Courses”.

Figure 2.2: Smart badges: The Active Badge by Palo Alto Research Centre
(Weiser, 1999)
2008; Pentland, 2010; Dong et al., 2012), shown in Figures 2.3 and 2.4. These badges,
containing tri-axial accelerometers, are able to capture some characteristics of the motion
of the wearer (e.g. being still, walking, gesturing). Thanks to additional sensors such as
infrarred transceivers, they are also able to capture face-to-face interaction time. Being
lightweight and with a long battery life, these badges can be carried unobstrusively for
several hours a day.
Figure 2.3: Smart badges: Hitachi’s Business Microscope
(external and internal appearance) (Ara et al., 2011)
Watanabe et al. (2012) used the HBM in an office environment, finding evidence
that the level of physical activity and interaction with others during break periods
(rather than during working activities) is highly correlated with the performance of
their team. Watanabe et al. (2013) then applied this methodology within a learning

Figure 2.4: Smart badges: The MIT wearable sociometric badge (Dong et al., 2012)
environment, this time using the smart badges on primary school children, observing
a strong correlation between the scholastic attainment of a class and the degree of in
which its members are “bodily synchronised”. In other words, classes with all their
members are either physically active or resting consistently during the same periods,
perform better. Another correlation these authors observed is the number of face-to-
face interactions per child during break. Their findings suggest that when children in a
class move in a cohesive manner, the class perform well overall, and also, that the more
face-to-face interactions an individual has, the better their attainment.
The use of badges by all participants is easily enforced in an environment with a
strict dress code, such as school uniforms. Since our population of interest is higher
education students, smartphones are probably more appropriate than smart badges as
sensor carriers, but it is nonetheless interesting to see how much can be learned from sen-
sor data, especially when combined with learning analytics, as in the case of Watanabe
et al. (2013), certain behaviours can be found to be related to a measure of success.
Smartphones present another advantage over badges. Equipped with ambient light
sensors, proximity sensors, accelerometers, GPS, camera(s), microphone, compass and
gyroscope, plus WiFi, Bluetooth radios, a variety of applications can be built to gather
a great range of sensed data Lane et al. (2010). Thanks to their communication and
processing capabilities, smartphones could support a sensing architecture such as the
one depicted in Figure 2.5.
Contextual information can be inferred from the sensor data hence gathered, and the
context determined as in, for example, location. However, it has been long accepted that
“there is more to context than location” (Schmidt, Beigl, and Gellersen, 1999). Contex-
tual information broadly falls into one of two types: physical environment context (such
as light, pressure, humidity, temperature, etc) and human factor related context such
as information about users (habits, emotional state, bio-physiological conditions, etc),
their social environment (co-location with others, social interaction, group dynamics,
etc), and their tasks (spontaneous activity, engaged tasks, goals, plans, etc) (Schmidt
et al., 1999).

Figure 2.5: A smartphone sensing architecture (Lane et al., 2010).
Context acquisition is, however, important not just because of the possibility to offer
customised services that adapt to the circumstances. Context processing can increase
user awareness (Andrew et al., 2007), and thereby prompt alternative actions to better
achieve a desired goal given the current context, hereby modifying somehow an intended
behavior.
2.3.1 Summary
The literature in this area indicates that sensor data has the potential to help us un-
derstand human behaviour as a collective and as individuals as well as gathering the
context in which it is situated. This would be a suitable foundation for a behavioural

intervention which is aligned to the user’s goals, and the smartphone is a suitable sensing
platform which could be used to understand users’ behaviour as well as supporting them
in achieving their higher goals, as discussed in the next Section.
2.4 Behaviour sensing and intervention
Despite its inherent complexity, researchers have shown that human behaviour is highly
predictable in certain contexts. In the context of scale-free networks, the degree of
predictability has been quantified to 93% (Song et al., 2010). Evidence suggests that
behaviour can be “mined” and even predicted using sensors on phones or smart badges
(presented in the previous Section):
• identifying structure in routine (for location and activity) to infer the organisa-
tional dynamics (Eagle and Pentland, 2006);
• analysing behaviour based on physical activity as detected via smartphones (Bieber
and Peter, 2008);
• predicting work productivity based on face-to-face interaction metrics (Wu et al.,
2008; Watanabe et al., 2012);
• inferring friendship network structure with mobile phone data (Eagle, Pentland,
and Lazer, 2009);
• using mobile phone data to predict next geographical location based on peers’
mobility (De Domenico, Lima, and Musolesi, 2012), even predicting when will the
transition occur (Baumann, Kleiminger, and Santini, 2013);
• classifying social interactions in contexts, where a crowd disaggregates in small
groups (Hung, Englebienne, and Kools, 2013);
• predicting personality traits with mobile phones (de Montjoye et al., 2013);
• Bahamonde et al. (2014) showed that even data from smart cards which can be
regarded as less personal than phones or identity cards are suitable capable for
behavior mining. In particular, these researchers were able to deduce users’ home
address through the data exposed by their bip! cards, which are used for payment
for public transport in Santiago de Chile.
From this research we can assert that, given sufficient information, some human be-
haviour can be predicted (see Appendix B for more on its high predictability).
Specifically relevant to behaviour sensing in the educational context is the possibility
of “seeing” the learning community (Dawson, 2010) by studying the frequency and types

of interactions amongst learners using social network analysis (SNA), as factors such as
degree centrality5 is a positive predictor of a student sense of community, which is
measurable.
Srivastava, Abdelzaher, and Szymanski (2012) acknowledge the use of smartphones
for sensing is becoming increasingly commonplace for human-centric sensing systems
(whether the humans are the sensing targets, sensors operators or data sources). They
identify various technical challenges to their wider adoption for these systems, one of
them being the difficulty of inferring a rich context in the wild. They warn that earlier
successes on inferences about mobility do not replicate with ease when making inferences
about “physical, physiological, behavioural, social, environmental and other contexts”
(my emphasis).
In terms of behavioral change, the state of the art includes:
• using computers as persuasive technologies6 (Fogg, 2003, 2009, 2003; Müller, Rivera-
Pelayo, and Heuer, 2012);
• promoting preventive health behaviors to healthy individuals through SMS, with
positive behavior change in 13 out of 14 reviewed interventions (Fjeldsoe, Marshall,
and Miller, 2009);
• health-promoting mobile applications (Halko and Kientz, 2010);
• HCI frameworks for assessing technologies for behavior change for health (Klasnja,
Consolvo, and Pratt, 2011);
• “soft-paternalistic” approaches to nudge users to adopt good behaviours to protect
their own privacy on mobile devices (Balebako et al., 2011);
• nonverbal behavior approaches to identify emergent leaders in small groups (Sanchez-
Cortes et al., 2012);
• interactions of great impact and recall to facilitate behaviour change (Benford
et al., 2012);
• protocols for behavior intervention for new university students (Epton et al., 2013);
• using smartphones for digital behavioral interventions (Lathia et al., 2013; Weal
et al., 2012);
• guidance for planning, implementation and assessment of behavioral interventions
for health (Wallace, Brown, and Hilton, 2014).
5
The degree centrality is defined by the number of connections a given node has.
6
Persuasive technologies, not to be confused with pervasive, as here the emphasis is on “persuasion”
rather than ubiquity.

In particular, Wallace et al. (2014) argue that interventions involve change processes
“linked to psychological theories of human behaviour, cognition, beliefs and motivation”
with a primary aim of improving experiences and well-being. This must be incorporated
in the planning and implementation of any behavioural intervention, in particular for
digital interventions. Lathia et al. (2013) identify the need for monitoring, learning
about the behaviour, before delivering an intervention, effects of which must continue
to be monitored (Figure 2.6).
Monitor
• Gather mobile sensing data
• Collect online social network
relationships and interactions
Learn
• Develop behaviour models
• Infer when to trigger
intervention
• Adapt sensing
Deliver
• Tailored behaviour change
intervention
• User feedback via the smart-
phone
Figure 2.6: The three components of digital behaviour interventions using
smartphones (Lathia et al., 2013, adapted).
Furthermore, Klasnja et al. (2011) assert that the development of such technolo-
gies presupposes the need for large studies, suggesting that “a critical contribution of
evaluations in this domain, even beyond efficacy, should be to deeply understand how
the design of a technology for behavior change affects the technology’s use by its target
audience in situ”. Translating this experience to the educational context means that it
is not realistic to measure the success of the development by actual behavior change,
but instead, by the degree of understanding of its potential to influence behaviour.
2.5 Final comments
In the previous section, smartphones and badges were considered as sensing platforms for
behaviour. In addition to the data that could be collected implicitly (i.e. without explicit
intervention from the user) via these, the possibility of incorporating user-generated data
is also valuable. As an example, life annotations (Smith, O’Hara, and Lewis, 2006) and
‘lifelogging’ (O’Hara, 2010; Smith et al., 2011). This data could be potentially used to
enrich that typically studied in learning analytics by giving an insight on an additional
dimension of student lives: what do they do when they are not studying?

Through this (still ongoing) survey of the relevant literature, I have now gained a
greater understanding of the characteristics of Higher Education students (which may
condition their levels of academic success), the devices they use in their learning (in
and out of the classroom), and others from which their behaviour can be sensed, as
behavioural factors may complement conditioning factors in determining of student suc-
cess. I also explored the state of the art in behavioural interventions, and what data can
be used to facilitate one. This is the foundation upon which key research components
have been created, which are presented in the next Chapter.

Chapter 3
A research question
The literature review presented in the previous Chapter surveyed the type of data and
techniques that can be used to understand and predict student behaviour. This Chap-
ter formulates the research question to be addressed, in order to plan an experimental
methodology and a road map for future work.
The research question stated in the introduction is “What are the measurable factors
for the prediction of student academic success?”. This Chapter discusses conditioning
and behavioural factors affecting students academic success and how to gather data for
measures of these factors against academic performance (a proxy for success).
3.1 What are the measurable factors for the prediction of
student academic success?
Most context-aware pervasive systems use location as the most important contextual
information available. Indeed, there is a wealth of research and commercial products
which offer location-based services, which focus on the use of readily available informa-
tion relevant to users in a given location. Not yet so well exploited, although gathering
significant scientific interest, is the use of physical activities as contextual information.
Other sources of contextual information that can become readily available include
the use of social media and learning analytics. Additionally, using sentiment analysis
on social media could help capture users mood and general outlook over the observable
period. Data mining algorithms could be applied over collected data, however, the
“ground truth” measure of what constitutes a successful student needs to be established
beforehand, and as explained earlier, it is in itself a very difficult question. Proxy
measures of success can be used, such as academic achievement and progression, but
other aspects of student life such as level of engagement and contentedness (if somehow
18

Chapter 3 A research question 19
measurable) could also taken into account for a more complete portrait of a successful
student.
Table 3.1 lists a range of activities that students in higher education are likely to
engage in, as well as the means of gathering data which could lead to identify a given
activity, assuming participants’ consent and unrestricted access to data sources, and the
practical viability of the creating such a data collection based on existing research. As
Table 3.1 suggests, a substantial amount of information about the student behaviour can
be harvested and quantified (albeit exhibiting “Big Data” challenges for any practical
purposes). In other words, it is viable to investigate the behavioural factors affecting
the student success, if, as in the traditional learning analytics (based on conditioning
factors1), these are analysed against metrics of academic success, such as retention,
progression and completion. This would give a more complete characterisation of a
student than ever before and, as a consequence a more powerful, accurate prediction of
their success.
I have now specified the research question, and will now discuss the practical work to
date conducted in pursuit of answers of aspects of this question, arisen from the literature
review presented in Chapter 2. This is followed by the formulation of specific research
hypothesis, which will specifically qualify the scope of this research (in Chapter 5).
1
Conditioning factors such as, for example, those highlighted in Table 5.2, page 38.

Chapter 3 A research question 20
Table 3.1: What do students do?
Activity What could be measured? Possible
data source
Research using
“similar” data sources
Attend
lectures
Number of lectures attended
during the semester, punctu-
ality (by comparing calendar
against actual arrival times)
GPS, University
timetable, co-
location with peer
learners, wi-fi
Ara et al. (2011); Watan-
abe et al. (2013); Wu et al.
(2008); Pentland (2010);
Dong et al. (2012)
Use
a VLE
Forum participation (fre-
quency, number of posts),
number of downloads
VLE records Barber and Sharkey
(2012)
Visit
libraries
Number of items borrowed,
length of the loan, medium,
material type
Smartcard,
Radio-Frequency
Identification
(RFID), library
records
Take
exams
Academic performance mea-
sures (exam results, history of
academic performance)
University
records, VLE
Travel Mode of transport, Distance
travelled, peridiocity
Accelerometer,
transport smart
card records, GPS
Hemminki, Nurmi, and
Tarkoma (2013a); Baha-
monde et al. (2014)
Meet other
students
Co-location with other learn-
ers, certain locations (labs,
etc), noise levels at location
GPS, Bluetooth,
microphone,
smartcard, RFID
tags
Hemminki, Zhao, Ding,
Rannanjärvi, Tarkoma,
and Nurmi (2013b)
Extra-
curricular
activities
Participation in societies,
sports, games, etc
VLE forums,
Facebook
Wen et al. (2014)
Social
networking
Number and frequency of
tweets and facebook posts,
number of uploaded photos
Twitter,
Facebook
Physical
activities
Frequency, level of activity
(walk, cycle, run), fidgeting?
Accelerometer,
gyroscope
Hung et al. (2013); Huynh
(2008)
Play and
rest
Number of hours watching TV
or movies
Lifelogging, ambi-
ent light sensors,
accelerometer
Smith et al. (2011)
Other
activities
of daily
living
Eating and drinking (regular-
ity of meals, frequency)
Lifelogging Smith et al. (2011)
Social
networking
Number and frequency of
tweets and facebook posts,
number of uploaded photos
Twitter, Face-
book

Chapter 4
Outcomes of Work to Date
In addition to the literature review presented in Chapter 2, other work to date has
involved the investigation of student’s views via two surveys applied to Higher Education
Students, one in English, of students in the UK (Section 4.1) and a version in Spanish,
of students at the University of Chile (Section 4.2), as well as an investigation into a
platform and its dataset from which student behaviour could be inferred: the U-Cursos
platform (Section 4.3).
4.1 Survey of HE English-speaking students
4.1.1 Methodology
A survey1 of Higher Education students, including undergraduate and postgraduate stu-
dents in several disciplines, was applied between the 16th August and the 18th October
2013. This survey focused on exploring the current use of smartphones by Higher Ed-
ucation students as well as establishing acceptability of a future application. It was
developed iteratively, applying early versions amongst fellow researchers before deploy-
ing it on the survey platform iSurvey. Data collected using early versions of the survey
was discarded as their purpose was only to inform the design. The questions appearing
in the final version of the survey can be seen in the Appendix C.
Some of the elements in the literature review informed the questionnaire design. For
example, the exploration the use of the smartphone that Questions 2 and 3 intended to
test the extent to which the characterisation of a virtually “tethered” student presented
in Section 2.1.1 is true. Similarly, the considerations presented in Section 2.1.2 helped
in determining the age groups within question 5(b). In all, the information required fell
across the following areas:
1
Hosted at https://www.isurvey.soton.ac.uk/admin/section_list.php?surveyID=8728.
21

Chapter 4 Outcomes of Work to Date 22
• Smartphone ownership — to establish whether participants own (or intend to
acquire) a smartphone shortly. If so, which brand, to confirm whether an Android
development would be suitable.
• Current use of the smartphone — in which participants are asked about the fre-
quency of their use of their phone across a range of activities.
• Perception on whether the smartphone helps or hinders participants’ personal goals
in general, and their academic success specifically.
• Acceptability of a pervasive application that would provide behavioural “nudges”
and desired features of such an application;
• Other information controlled including: discipline studied, level of study, modality
of studies (part-time or full-time) and views on adoption of technology.
The survey was publicised on various social networks (LinkedIn, Facebook and Twit-
ter) as well as by direct e-mail invitation to University of Southampton students2. Par-
ticipants were required to be students in Higher Education and over 18 years old. No
compensation was offered as no detriments arose from the participation in the research
other than an investment of ten minutes for the typical participant (of which partici-
pants were duly warned beforehand) and participants were not required to give sensitive
information, as questions related to the demographics section of the survey were not
open (instead, meaningful bands were offered for selection whenever possible). Many
questions could have been skipped if the participant wanted so3.
A total of 807 students attempted this questionnaire however, many could not com-
plete due to a limitation of the iSurvey platform, which hosted the survey4. After
discarding incomplete submissions and those from participants in academic institutions
outside the UK, data from 164 participants remained for analysis.
4.1.2 Findings
An analysis of the responses indicate that participants, despite actively using smart-
phones in their daily lives, are hesitant on allowing these devices to track their behaviour
2
Via Joyce Lewis, Senior Fellow for Partnerships and Business Development.
3
Compliant with recommendations by the British Educational Research Association (BERA), out-
lined in “Ethical Guidelines for Educational Research”, http://www.bera.ac.uk/system/files/BERA%
20Ethical%20Guidelines%202011.pdf. Also compliant with our institutional guidelines collated un-
der https://sharepoint.soton.ac.uk/sites/fpas/governance/ethics/default.aspx, (both last ac-
cessed 28th
February 2014). Ethics reference number: ERGO/FoPSE/7447.
4
At the time, there was a requirement for the participants to have Flash-enabled devices to complete
surveys with slider questions (as it was the case), so participants accessing via iPhones or iPads had
to re-start the survey in other platforms. It is not possible to estimate how many did (given that the
survey was anonymous). This problem has now been resolved (https://www.isurvey.soton.ac.uk/
help/changes-to-the-slider-question-type/) but unfortunately it affected this data collection.

and whether such feedback is desirable. On one hand, participants report their use of a
smartphone for a number of activities, as shown in the charts in Figure 4.1.
Figure 4.1: Survey responses from UK students (excluding qualitative data).
The first 18 charts refer to activities that participants report undertaking with their
smartphones, which correspond to the 18 activities indicated in Question 2 of the survey.
A dominance towards lower numbers in the x axis corresponds to a high frequency in
performing a given activity as reported by the participants. For example, this applies to
making or receiving phone calls and text messages, using social networks and calendars
or reminders. Conversely, a dominance towards higher numbers in the x axis corresponds
to a low frequency, as it is the case for blogging, searching for a job, and playing podcasts.

The next two charts in Figure 4.1 show the reported purpose for participants to use
their smartphone both in term time and outside of term. Whilst there is a preference
towards the use of their smartphones for personal reasons, as expected, this was much
more marked for outside of term periods. With regards to the perception of their phone
being a help or a barrier towards their personal goals and their academic success (the
subsequent two charts), most participants leaned towards the left end of the spectrum
(a help).
Figure 4.1 also indicates the reported desirability of features of a future smartphone
application, in charts 23 to 28. In this case, a preference towards the left indicates that
the given category is very desirable, and towards the right that it is not. Participants
were then asked whether they were concerned about any of these possible features5. In
this case, and with various degrees of acceptance, the majority welcomed features that
provided them with information about themselves and their peers, with the exception
to the check-in learning spaces, which is not desired for the majority of the participants
in the survey.
Out of 164 participants, as many as 95 reported no concern about the features
mentioned. The remaining 69 participants had a variety of concerns, more prominently
regarding feedback on their behaviour and about their peers, as well as privacy concerns
regarding the capability of an application to check them when entering learning spaces.
Other privacy concerns focused on the data itself, and who would access and control
it. Many commented they would not want their smartphones to have these features,
in particular those regarding physical activity tracking (terms such as “surveillance”,
“big brother” and “panopticon” were mentioned) but some others would welcome some
feedback on how they use their time and see the benefits of using such an application.
However, not all respondents have the same attitude towards adopting innovation6,
as they claim identification with one of Rogers (1962) taxonomy classes: “Innovators,
Early adopters, Early majority, Late majority, or Laggards”7.
4.2 Survey of students from the University of Chile
4.2.1 Methodology
Once it was decided to use data from the University of Chile students, it became relevant
to adapt the survey previously described in Section 4.1 for its application on these
5
See Appendix D for a word cloud based on participants’ responses.
6
Rogers’ taxonomy is succintly summarised as follows: Innovators: first to adopt an innovation; Early
adopters: judicious in balancing financial risks; Early majority: adopt an innovation with early adopters
advice; Late majority: adopt innovation after majority; “Laggards”: the last to adopt an innovation.
(Rogers, 1962)
7
Currently, this data is being analysed using NVIVO (for the open responses) and SPSS and
SigmaPlot, and further conclusions will be reported in the final thesis.

Figure 4.2: Survey of University of Chile students: First screen.
students8. As well as translating the content for each of the screens (see example 4.2),
a question was removed as it was not relevant within this context (the concept of part-
time studying is not formalised via registration), and further options were added to the
educational stage question (as graduate courses last typically a minimum of 5 years, as
opposed to the UK’s three-year courses).
4.2.2 Findings
The general trend of the responses is remarkably similar to that of UK students. Only
two exceptions, which are explained in the following paragraphs:
Firstly, the Chilean participants seem to prefer phone calls to SMS messaging. This
may be explained by the fact that each SMS text is typically charged (unlike in the
UK, where most providers offer a number of free messages as part of their services).
Given that Internet providers in Chile offer affordable flat-fare packages, for small texts,
Chilean students may prefer communicating via social networks (such as Twitter direct
messaging or Facebook chat), or messaging apps (such as WhatsApp and Viber).
A second difference worth commenting is that whilst the UK participants perceive
their smartphones as helpful towards the achievement of both their personal goals and
their academic success, this is not so clear for the Chilean participants, who seem divided
in their responses. Although the justification for this difference is yet to emerge from
8
The version of this survey in Spanish is hosted at https://www.isurvey.soton.ac.uk/admin/
section_list.php?surveyID=10807 (closed at present).

Figure 4.3: Survey responses from students of the University of Chile (excluding
qualitative data). Note that it has one chart less than Figure 4.1 because there is no
distinction between Full- and Part-Time at registration at the University of Chile.
further analysis of the data, one possible explanation may lie with the stage in their
studies: it is conceivable that students who have not progressed as quickly as they had
expected may attribute their lack of progress to distractions related to their use of their
smartphones, which is nevertheless, comparable to that of their UK counterparts.

4.3 U-Cursos
U-Cursos is a web-based platform designed to support classroom teaching. An in-house
development by the University of Chile, it was first released in 1999, when the Faculty of
Engineering required the automation of academic and administrative tasks. In doing so,
the quality and efficiency of their processes improved, whilst supporting specific tasks
such as coordination, discussion, document sharing and marks publication, amongst oth-
ers. Within a decade, U-Cursos became an indispensable platform to support teaching
across the University, used in all 37 faculties and other related institutions.
Channels Service content
Channels services
Figure 4.4: A typical U-Cursos view. Left: a list of current channels (courses,
communities and associated institutions). Top right: services available for the selected
channel. Bottom right: contents of a service. From Cádiz et al. (2014) (in Appendix
E)
The success of U-Cursos is demonstrated by the high levels of use amongst students
and academics, reaching more than 30,000 are active users in 2013. U-Cursos provides
over twenty services to support teaching, as well as community and institutional “chan-
nels”, which allow students to network, share interests and engage in discussion about
various topics. Figure 4.4 shows a typical view of U-Cursos. On the left, a list of
“channels” available for the current term are shown. Channels are the “courses”, “com-
munities” and “institutions” associated with the user. Typically, courses are transient,
so they are replaced with new courses (if any) at the start of the term. Communities
are subscription channels which are permanent and typically refer to special interest
groups, usually managed by students, with extracurricular topics. Finally, institutions

Figure 4.5: Cramped look to the U-Cursos web interface from a smartphone (Cádiz
et al., 2014).
refer to administrative figures within the organisation. The institutional channels are
used to communicate official messages on the news publication service and also to allow
students to interact using forums containing students from all of the programmes within
each institution.
A number of services are available for each type of channel. Users can select any
of the shown services and interact with it on the content area of the view. Note that
the majority of the services are provided for all types of channels, but courses also offer
academic services such as homework publication and hand-in, partial marks publication
and electronic transcripts of the final marks. These features make course channels official
points of access for the most important events in a course and have become indispensable
for students.
4.3.1 Current status
The current version of U-Cursos displays well on all regular-size screens (above 9”), such
as desktop computers and tablets. However, the user interaction becomes cumbersome
on small displays, such as those in smartphones, as shown in Figure 4.5.

300,000
600,000
900,000
1,200,000
1,500,000
1,800,000
2,100,000
2,400,000
2,700,000
3,000,000
hits
month
1st term 2nd term student strike
Figure 4.6: Access graph between 2010 and 2014 for U-Cursos (Cádiz et al., 2014).
Another shortcoming is the lack of notification facilities, in particular those alerting
users of relevant content updates. The current setting requires users to manually access
the platform repeatedly to confirm that the information is still current. This behaviour
can be observed in Figure 4.6, which shows access statistics of U-cursos in the last four
years. There are clear high-peaks during the end-of-term periods9.
Additional factors may trigger an increased access rate to the service: students ask
more questions and download class material for the final exams, project coordination,
amongst others. According to the users, there is a component of uncertainty which
encourages users to repeatedly access the platform during these periods. As a response,
researchers from ADI designed a mobile application for the platform, currently in beta
testing.
A research visit to NIC Labs (University of Chile), took place from the 9th to the
19th of March 2014, to provide access and understanding of the historical data collected
across the University and also study the platform itself. A paper on the collaboration
was written and submitted to the 28th British HCI Conference, (see Appendix E).
U-cursos offers a number of services, of which the most frequently used are shown
in Table 4.1, with an indication of how popular are they amongst users as well as a list
of features students would like to see in U-Cursos (both for mobile and web).
The unique advantage of using this data above any other dataset currently available
is that it has over 30,000 users (staff and students) covering the past ten years, therefore
it is in principle viable for longitudinal and cross-sectional analysis. Whilst the mobile
platform is still in beta testing, having access to this wide range of data would enable
its analysis via educational analytics.
9
Terms run from March to July and from August to December in Chile. Some events may induce
small variations on the actual dates. The university closes for summer holidays in February. Source:
http://escuela.ing.uchile.cl/calendarios (In Spanish - Last accessed 9th
July 2014).

Table 4.1: U-Cursos services ranked in ascendent order of popularity amongst users.
The number in parenthesis indicates the percentage of students who flagged the relevant
service or feature as especially useful or desirable (Cádiz, 2013, adapted).
Current services New mobile features New general features
My timetable (92) Granular push (20) Chat (39)
E-mail (74) Preview material (11) Library (7)
Notifications (70) Search for a room (10) Multiplatform (6)
Teaching material (58) More simplicity (9) Tablet support (6)
Calendar (50) Attendance log (5) Facebook integration (4)
Partial marks (46) People search (4) Campus map (3)
Forum (20) Offline access (4) Room status (2)
Dropbox (14) Book a lab (4) Staff timetable (2)
Guidance notes (11) Timeline (4) “Read later” (2)
Coursework (7) Certificate requests (4) Virtual Classroom (2)
News (7) Android widget (4) Notes bank (1)
Access to past courses (5) Marks calculator (4) Health benefits (1)
Favourites (3) Google drive (3) Evernote integration (1)
Resolutions (2) Printing queues (2) Anonymous feedback (1)
Polls (2) Institutional mail (2) Foursquare integration (1)
Links (2) Enrolment (2) Group making (1)
Official transcripts (2) Course catalogue (1) Compare timetables (1)
Course administration (1) Find staff offices (1) Anonymous feedback (1)
Posters (1) Shortcuts (1) Reporting admin errors (1)
4.3.2 Summary
This chapter has described the practical experiences in my research, in particular, those
related to the application of a survey amongst two different groups of HE students,
and those related to the process of securing a dataset from which a model of student
behaviour could be created in answering our first research question. This foundational
work inform the steps for future action, described in the next Chapter, which lays out
a plan for the following months up to the final thesis submission10.
10
Further work identified yet beyond the scope of this thesis is presented in Appendix A.

Chapter 5
Research Plan for Final Thesis
This research will explore the predictability of student success applying learning analytics
on big data sets. In particular, I will analyse a rich “data trail” of student activities
as gathered via their interactions with a Learning Management System (LMS), such as
the University of Chile’s U-Cursos1. This data can be combined with data captured by
the institution at first enrolment, such as socio-economic indicators (typically used in
traditional learning analytics). From this analysis, a model of academic success will be
developed, providing insight on the factors influencing academic performance amongst
other measurable proxies for success.
5.1 Motivation
A primary motivation behind seeking such an insight is that it would facilitate the
identification of students “at risk”, and further enable behavioural interventions so that
students can be supported in becoming successful in their studies. A greater, lasting
goal would be to influence student behaviour via persuasive technologies, so that the
students themselves are empowered to effect a significant change in their study. However,
this is a long-term goal beyond the scope of the present research. Whilst the rich
interconnection necessary for a digital behavioural intervention is not yet fully supported,
and the existing student data is both incomplete and noisy for this specific purpose, we
can still gain a good understanding of how it might look by examining current student
data, from both the educational and the pervasive computing perspectives.
A central theme of this research is learning analytics, informed by relevant studies on
behavioural interventions and the application of pervasive computing to education. In
order to build on the traditional learning analytics research approaches (generally limited
1
Developed by the University of Chile’s Information Technologies group (ADI, Área de Infotecnologı́as
in Spanish).
31

Chapter 5 Research Plan for Final Thesis 32
to data controlled by the educational institution), I have also considered including data
that could offer an additional insight into student behaviour, by articulating descriptions
of the activities successful students do even when they study.
5.2 Research question and research hypotheses
The general research question to be addressed is:
“What are the measurable factors for the prediction of student academic
success?”
This is a very wide-ranging question, which includes a number of conditioning fac-
tors (e.g. what students bring with them before starting Higher Education) as well as
behavioural ones (e.g. how do students engage in Higher Education studies). To focus
the research, a number of specific research hypotheses have been identified:
H1: Traditional learning analytics on conditioning factors are suitable pre-
dictors of success. Specifically, are socioeconomic indicators and student com-
petences2 acquired during secondary schooling adequate predictors for student
performance in Higher Education? Existing research has strongly indicated this
to be true, however the work published to date contains limitations, such as:
(a) in the size of the sample. For example, Bhardwaj and Pal (2011) studied data
from up to 300 participants;
(b) studies predicting only persistence or attrition rather than measured academic
performance (Glynn et al., 2003)
My investigation of H1 is designed to extend the scope of the analysis and remove
some of these limitations. However, since this and other work published to date
highlight some factors as good predictors of student success, I will especially look
for evidence of such a correlation in the data to either support or falsify hypothesis
H1. These factors are: socio-economic factors such as age and parents level of
education, as well as academic performance in previous learning (such as high-
school marks).
H2: Learning analytics data in the traditional sense can be significantly
enriched by incorporating data from social media and other student-
generated data. Students interacting with the LMS leave a data trail which can
be quantified. Engagement in social forums within the U-Cursos platform is an
additional variable that can be incorporated in the prediction model. Does the
model become more accurate by doing so?
2
By student competences we refer to those measured by the University Selection Test in Chile (or
PSU, Prueba de Selección Universitaria in Spanish (Dinkelman and Martı́nez A, 2014)), which is used
for university admissions across the country.

H3: Smartphone data can be used to inform the prediction model. In par-
ticular, do measures of engagement with the U-Cursos mobile platform correlate
with those in the web-based version (for which there is substantial historical data
available)?
To test hypothesis H1, I will work with institutional data held by the University
of Chile via the platform U-Campus3, which holds databases on administrative data
related to each student, e.g. status, courses in which they are enrolled, enrolment, pro-
gression, withdrawal and completion, as well as the reported socio-economic indicators
at the time the PSU test ( Prueba de Selección Universitaria in Spanish) was taken. U-
Campus offers a number of services to five4 faculties across the university: those services
related to curriculum management (e.g. enrolments, course programmes, prospectuses,
accreditation), administration and personal management (e.g. repository of University
Council minutes, accreditation statistics).
U-Campus is of interest for this research since the student data held (as above
outlined) could well be used to predict success if H1 is true. In particular, and following
on previous research (Sarker, 2014; Bhardwaj and Pal, 2011; Glynn et al., 2003), I expect
to find a correlation between academic performance and socioeconomic indicators such
as education level and occupation of the parents,
To test hypothesis H2, I will include in the analysis log data from U-Cursos in-
dicating the time and frequency of interactions with the LMS, including not only the
instances in which students upload content (e.g. submitting coursework) but also the
instances in which they retrieve information of interest (e.g. assessment results and
course information).
In testing hypothesis H3, I will follow closely the development of the mobile ex-
tension of U-Cursos, which aims firstly at improving accessability and usability, and
secondly at exploiting smartphones capabilities, such as nudges via granular pushes for
delivery of information and the possibility of incorporating location data to the times-
tamp of an interaction. Rather than investigating the effectiveness of these additions,
I’m interested in proposing a framework so that mobile data can be incorporated into
the learning analytics.
There are certain limitations regarding the mobile data which will be available in
the coming months. In particular, this development is still in progress: beta testing
is expected to finish by the end of July 2014 and therefore there is no historical data
available. Additionally, the number of users is currently limited to just 50 (as opposed
to the current 30,000 users of the web-based version of the platform). Despite this
limitation, it is worth exploring whether the prediction model applied using the mobile
3
Access-restricted portal: https://www.u-campus.cl. See Appendix F for screenshots.
4
The University of Chile faculties currently using U-Campus are: Mathematical and Physical Sci-
ences, Medicine, Architecture and Landscaping, Social Sciences, and Philosophy.

data is reasonably aligned with the prediction results achieved when using the web-based
platform.
5.3 Work Packages
In order to test the hypotheses presented in the previous section, a number of activities
have been planned. The timescales for the proposed future work are given in the Gantt
chart in Table 5.1, and detailed in the following work packages:
WP1: Enhanced literature review, with a focus on learning analytics as applied to the
three research hypotheses.
WP2: Additional data analysis on surveys conducted in Chile and the UK.
WP3: Data acquisition and the collation of a complete dataset (a subset of U-Campus
and U-Cursos).
WP4: Analysis of historical data from the PSU admission test of University of Chile
students, for indicators associated to completion (available via U-Campus).
WP5: Analysis of U-Cursos data, for factors associated with high marks.
WP6: Integrating WP4 with WP5 findings for a predictive model of academic success.
WP7: Incorporating the additional variables gathered via U-Cursos mobile into the
predictive model from WP4.
I am currently working on the first three work packages (WP1 to WP3). WP1 is
necessary to complement my existing literature review, and will continue for the next
12 months, to ensure awareness of state-of-the-art research. In WP2, I will finalise the
quantitative and qualitative analysis of the surveys data that was described in Chapter 4.
WP3 also completes ongoing work, this time regarding the datasets needed to work in
this research. Work for this package started during my research visit to the University
of Chile from the 9th to the 19th of March 2014, when an improved understanding of the
data architecture of both U-Cursos and U-Campus was achieved (beyond the general
concept presented by Cádiz (2013)). During this trip the collaboration with ADI and
NIC Labs became formally established. Figure 5.1 provides an outline of the processes
and the kind of data stored, as well as the domains of responsibility for each.
WP4 will undertake a full analysis and evaluation of the PSU test data of students
who have enrolled in the University of Chile since 2003, when the test was first intro-
duced. More specifically, I will study correlations and statistical dependencies (using

Chapter
5
Research
Plan
for
Final
Thesis
35
Table 5.1: Schedule of research work and thesis submission
2014 2015
Jul Aug Sep Oct Nov Dec Jan Feb Mar Apr May Jun Jul Aug Sep Oct
Mini-thesis viva
H1 – conditioning factors
WP1: Extending literature review
WP2: Additional data analysis on surveys data
WP3: Securing U-campus and U-cursos data
WP4: Analysis of U-campus data (with PSU data)
Second research visit to Chile
H2 – behavioural factors
WP5: Analysis of U-Cursos data (SPSS and WEKA)
WP6: Integration for a predictive model
Submit WP6 results to Computers and Education
H3 – smartphone data
WP7: Incorporating mobile data
Working with visiting researcher from Chile
Thesis write-up
Thesis submission

U-Campus
U-Cursos
Monthly
forum
“dump”
PSU
ADI
Manual
enrolments
at Faculty
level
Students
automated
enrolments
Digitalisation
(some)
Digitalisation
Institutional
information
Student RUT,
name, address,
socioeconomic
data, age, etc
Course data (e.g. syllabus,
resources, coursework
specs, timetable, news,
student polls)
Student data (e.g. RUT,
names, email addresses,
avatars, courseworks,
partial marks, timetables,
final marks or fail status
(R/E/I))
U-Cursos
Mobile Lecturer/instructor data
(e.g. roles, courses,
permissions)
STI
Figure 5.1: Data architecture at the University of Chile: U-Campus and U-Cursos,
with processes and entities responsible for their management: ADI is the University of
Chile’s Information Technologies group (Área de Infotecnologı́as in Spanish) and STI
is the University of Chile’s Division of IT and Communications (Dirección de Servicios
de Tecnologı́as de Información y Comunicaciones ).
SPSS) between “conditioning” factors and the academic performance to date as mea-
sured by the PSU test. Table 5.2 shows the data fields available for this test5, with marks
(X) next to those which are of interest for this analysis, in particular: socio-economic
indicators and the average high-school marks, since they are generally accepted as re-
liable predictors of academic performance in the literature. Additional factors, such as
gender, age and nationality have been identified in the global literature as influential,
therefore I will also incorporate this data. Specifically for the Chilean case, it has been
reported that the PSU test is widely regarded as being biased towards school-leavers
of private schools and towards the metropolitan area. Therefore, I will also study the
impact of the educational institution of origin and the home city on the academic per-
formance prior to the test (in this work package) and then later in Higher Education
(in WP5). Finally, after certain pre-processing6, other fields (marked with †) are also
5
See Appendix G for further details, including screenshots of a sample student application.
6
In order to guarantee anonymity, it is necessary to avoid sensitive data, such as the name, phone
numbers, email, exact home address (street and house number), and exact date of birth (month and
year will suffice).

necessary. In particular, I will require the national identification number (hashed or
otherwise protected), since this will act as a unique key which could be used to link the
data from the PSU test (“conditioning data”) to the measures of academic performance
available via U-Cursos in WP5.
At this point, I will have sufficient evidence to either support or reject hypothesis
H1 (“traditional learning analytics on conditioning factors are suitable predictors of
success”), as indicated in the Gantt chart (Table 5.1). My findings will be discussed
with researchers in ADI and NIC Labs during my second research visit (for two weeks,
exact dates TBA), where I will complete the analysis and commence work on WP5.
The visit will be used also to agree with these researchers on measurable behavioural
factors that are feasible to study via the smartphone extension of U-Cursos, which will
be required for WP7.
For WP5, data from U-Cursos will offer some information on measures of academic
performance and “behavioural factors”, limited to how students interact with the plat-
form, in terms of type and frequency of their access, including coursework submission
information and interim assessments. This data will be analysed and correlations and
statistical dependencies will be studied (using SPSS). Additionally, I will apply data
mining techniques to formulate a prediction model of successful performance, consider-
ing these variables as classifying features.
WP6 concerns the integration of the conditioning factors (as gathered from U-
Campus) and behavioural factors (from U-Cursos). Since the number of variables
available will increase significantly, it is essential to apply feature selection methods
to improve the model and avoid overfitting. A number of classification methods from
the data mining toolset WEKA could be used, for example Naı̈ve Bayes, which has been
also used by Bhardwaj and Pal (2011) to predict academic performance7. As an outcome
of this work package, I intend to submit a research paper to the journal Computers and
Education8, where the evidence gathered to prove or disprove hypothesis H2 will be dis-
cussed. The effort in writing this paper will count towards the task “Thesis write-up”,
shown last in Table 5.1), hence this is shown as formally starting at the same time as
WP6, though in practice the writing takes place throughout the research project. Fi-
nally, WP7 concerns entirely in testing hypothesis H3 (“Smartphone data can be used
to inform the prediction model”), and will incorporate data from U-Cursos mobile to
the model created as part of WP6.
7
Bhardwaj and Pal (2011) only used conditioning variables such as those to be studied in WP4.
8
Some of the journal Computers and Education impact metrics are: Impact per Publication (IPP)
of 3.720 and Impact Factor (IF) of 2.775. As reported at http://www.journals.elsevier.com/
computers-and-education/ (last accessed on the 4th
July 2014).

Table 5.2: University Selection Tests (Prueba de Selección Universitaria, PSU) data
fields. Data from fields marked in bold will be used to validate H1, complemented
with other fields of interest (marked X). Note that fields marked † will require some
preprocessing for anonymisation. (Based on http://www.demre.cl/instr_incrip_
p2014.htm. Last accessed: 3th
July 2014).
Personal data (Comments)
Full name prefilled on login
† National identification number prefilled on login
X Country of nationality
X Gender prefilled on login
† Date of Birth prefilled on login
X Occupation two choices: Student or blank field
School data
X Type of applicant either from current or previous years
X Educational Institution prefilled
Educational Branch institutions may have several ones
X Year of graduation from High School prefilled
X Average high-school marks prefilled if from previous years
Geographical Area prefilled
Test choices data
Test choices Social and/or pure sciences (but just one
amongst Biology, Physics and Chemistry)
Admissions office
Test venue dropdown menu
Personal contacts
Home address: street, number
X Home: city, region and province dropdown menus
Phone numbers
E-mail address
Socio-economic data
X Marital status dropdown menu
X Work status dropdown menu
X Working hours dropdown menu
X Number of working hours a week
X Term time type of accomodation dropdown menu
X Household size
X Number of people in the household
in employment
X Who is the head of the household? dropdown menu
X Are your parents alive?
X How many people study in your
household
discriminated by educational stage
X Have you studied in a Higher Educa-
tion Institution
Yes/No
X If so, type of institution dropdown menu
Name of institution
About each parent
X Occupation multiple choice
X Industry multiple choice
Funding and payment
X Are you a beneficiary of a junaeb
scholarship?
dropdown menu

5.4 Contingency research plan
The research plan above described is predicated on acquiring specific data from a sub-
stantially large group of students, in particular, U-Campus, U-Cursos and U-Cursos
mobile. Although I have successfully established the appropriate contacts at the Uni-
versity of Chile (in the ADI group and with NIC Labs), and substantial progress has
already been made towards accessing U-Cursos and U-Campus data, a contingency plan
is in place for the event of failure to secure suitable data.
My contacts from the University of Chile have been forthcoming in answering my
questions as I become familiar with the platform and the organisation itself. My con-
tribution in this collaboration is that my findings will be used to inform the evolution
of the platform and further extensions are likely to incorporate “nudges” for a future
digital behavioural intervention seeking to improve retention and shortening the length
of time students need to graduate. Our close collaboration is already fruitful, as during
my research visit last March, we were able to prepare a research paper together where
U-Cursos is well described (Cádiz et al., 2014, as in Section 4.3). However, despite this
strong assurances evidencing their willingness for sharing the relevant data with me,
there are some practical issues to be resolved which may affect the feasibility of securing
the data as planned. In particular, the data architecture seems to have followed an
ad-hoc design and there are many redundancies and inefficiencies of which I have just
began to become aware. Being distributed across a number of tables, many a time on
separate sites, it is not a matter of simply being granted access to a centralised reposi-
tory. In addition, our requirement for anonymisation of the data adds another level of
uncertainty (which is hard to quantify) as this clearly will require time and effort by my
Chilean colleagues.
Should it be the case that the contingency research plan is carried out, hypotheses H1
and H2 may alternatively be tested on data from the University of Southampton Massive
Open Online Courses (MOOCs)9, which are run by the University of Southampton via
Future Learn.
Data regarding several conditioning factors to test hypothesis H1 are also harvested
during enrolment in these courses as part of a “pre-course” questionnaire. These include
socio-economic indicators (e.g. age, country, gender, employment status and reported
disabilities if any), and other conditioning factors such as course expectations, reported
learning preferences, subject areas of interest, and prior education (both in formal edu-
cation and in other MOOCs). Given this data, a similar study as that planned for WP4
can still be undertaken but using this data instead.
9
As an example, the MOOC “How the Web is Changing the World” has had two intakes since
2012 (and is running for third time this October). Further details at http://www.soton.ac.uk/moocs/
webscience.shtml (last accessed on the 26th
June 2014).

With regards to the testing of H2, there are a number of datasets available, for which
there is implicit consent from participants for their use in research. These datasets are
files in Comma Separated Value (CSV) format, the most relevant being:
• the End of Course dataset – contains metrics such the proportion of those who
enrolled in the course (“Joiners”) has abandoned (“leavers”). Other characterisa-
tions include: “Learners”(those who have viewed at least one step of the course),
“active learners” (thouse who has marked at least one step as complete),“returning
learners” (those who completed steps in more than one week), “social learners”
(those who have left at least one comment), and “fully participated learners” (sic),
those who have completed a majority of the steps including all tests10.
• the Step Completion dataset – Note that each course has a number of “steps” that
need to be completed to succeed (typically watching a video, reading a text, or
completing an assessment). Each step can have a number of comments associated.
• the Quiz data – which would constitute a proxy for “marks” in the traditional
sense; and
• the Comments dataset – Table 5.3 is a detailed example of the structure of this
datasets, the Comments dataset.
A “post-course” questionnaire, though mainly intended as a course evaluation ex-
ercise (and therefore including questions where the student rates the course in several
ways), also helps in gathering other indicators of the learning behaviour, such as point
of entry (whether from the start of the course or later on), reasons for attrition (if the
course was abandoned) and specific learning behaviours adopted investigating dedication
in time and effort, reported frequency of access, reflection, collaboration (through social
media as well as via comments in a step within the course) and connectivity (devices
used to access the course and typical study places) as well as their use of prior learning.
Combined, these datasets record all the interactions between participants through
the platform and hold a complete record of achievement and progress as the students
take on the various tasks and assessments in the course.
Admittedly, hypothesis H3 cannot be tested using MOOCs data, but alternatively
we would formulate a domain-specific hypothesis applicable to online-only courses, as
opposed to face-to-face instruction supported by an LMS, which is the case of interest
in the current plan. Also in this case, a shift in focus will be necessary, an the literature
review presented in Section 2.2.3.
10
Thanks to Kate Dickens from the Centre for Innovation in Technologies and Education (CITE) for
facilitating this information.

Table 5.3: FutureLearn Platform Data Exports. Adapted from https://www.
futurelearn.com/courses/course-slug/). (Last accessed: 4th
July 2014, by Kate
Dickens (Project Leader for the Web Science MOOC).
Comments
id [integer] a unique id assigned to each comment
author id [string] the unique, anonymous id assigned to the author
user
parent id [integer] the unique id of the parent comment (i.e. the com-
ment this comment replies to)
step [string] the human readable step number (e.g. 1.13)
text [string] the comment text
timestamp [timestamp] when the comment was posted
moderated [timestamp] the time at which a comment was moderated, if at
all
likes [integer] the number of likes attributed to the comment
Peer Review - Assignments
id [integer] a unique id assigned to each assignment submission
(referenced by reviews)
user
text [string] the comment text
first viewed at [timestamp] when the assignment step was first viewed
created at [timestamp] when the assignment was submitted
moderated [timestamp] the time at which a comment was moderated, if at
all
review count [integer] how many reviews are associated with the assign-
ment
Peer Review - Reviews
id [integer] a unique id assigned to each assignment review
user
assignment id [integer] the id identifying the assignment reviewed
guideline one feedback [string] text submitted for the first guideline
guideline two feedback [string] text submitted for the second guideline
guideline three feedback
[string]
text submitted for the third guideline
created at [timestamp] when the review was submitted

5.5 Summary
This Chapter presented the motivation behind the research question “What are the
measurable factors for the prediction of student academic success?” and outlined three
research hypothesis associated to it. Two of these hypothesis consider conditioning
and behavioural factors as predictors of academic success, whilst the last one regards
smartphone data as suitable to inform a prediction model of success. In order to test
them, a number of work packages (WP1-WP7) are planned, with deliverables at specific
points in the time remaining until the submission of the final thesis. I have also outlined
a contingency research plan should the data expected from the University of Chile prove
difficult to obtain for unforseen circumstances.
The following Chapter will outline future work that has been identified yet is beyond
the scope of this research given the time and resources remaining.

Chapter 6
Conclusions
This research will explore the predictability of student success from learning analytics
on big data sets. In particular, we seek to analyse a rich “data trail” of student activities
as gathered via their interactions with a Learning Management System (LMS), such as
the University of Chile’s U-Cursos1. This data can be combined with data captured by
the institution at first enrolment, such as socio-economic indicators (typically used in
traditional learning analytics). From this analysis, a model of academic success will be
developed, providing insight on the factors influencing academic performance amongst
other measurable proxies for success.
A primary motivation behind seeking such an insight is that it would facilitate the
identification of students “at risk”, and further enable behavioural interventions so that
students can be supported in becoming successful in their studies. A greater, lasting goal
would be to influence student behaviour via persuasive technologies, so that the students
themselves are empowered to effect a significant change. This is a long-term goal beyond
the scope of the present research. Whilst the rich interconnection necessary for a digital
behavioural intervention is not yet fully supported, and the existing student data is both
incomplete and noisy for this specific purpose, we can still gain some knowledge of how
it might look by examining current student data, from both the educational and the
pervasive computing perspectives.
The central theme of this research is learning analytics, informed by relevant studies
on behavioural interventions and the application of pervasive computing to education. In
order to build on the traditional learning analytics research approaches (generally limited
to data controlled by the educational institution), I have also considered including data
that could offer an additional insight into student behaviour, by articulating descriptions
of what successful students do when they are not studying.
1
Developed by the University of Chile’s Information Technologies group (ADI, Área de Infotecnologı́as
in Spanish).
43

Chapter 6 Conclusions 44
An area of research in need of exploration has been successfully identified in this
upgrade report, which combines an extensive range of contextual information (e.g. that
gathered via smartphones, as well as other data available in the educational institution)
in order to understand students’ behaviour, and then to use this analysis to increase
their chances of academic success by facilitating reflection (and thereby encouraging
behaviour change). The general research question to be addressed is:
“What are the measurable factors for the prediction of student academic
success?”.
This is a very wide-ranging question, which includes both conditioning factors (e.g.
what students bring with them before starting Higher Education) and behavioural ones
(e.g. how do students engage in Higher Education studies). Therefore a number of
specific research hypotheses have been identified:
H1: Traditional learning analytics on conditioning factors are suitable predictors of
success.
H2: Learning analytics data in the traditional sense can be significantly enriched by
incorporating data from social media and other student-generated data.
H3: Smartphone data can be used to inform the prediction model.
In order to test those hypotheses, a number of activities have been planned. As
such a plan depends heavily on acquiring specific data of a substantially large group
of students, in particular, U-Campus, U-Cursos and U-Cursos mobile, a contingency
plan will use the University of Southampton’s MOOC’s data instead, however WP5 will
not be delivered in this case, as there will be no data available to test H3. In such
an scenario, an alternative hypothesis, relevant to MOOCs specifically will be proposed
instead.
I intend that my work will provide a better understanding of how to use learning
analytics on big data sets, in which the data available about students can offer an
insight into their learning behaviour. This research, whilst at present limited to users of
a specific LMS, will offer additional light in our understanding of how to use big data
to support students in their goals of academic success, in an imminent data-rich future.

References
Alessandro Acquisti. Nudging privacy: The behavioral economics of personal informa-
tion. IEEE Security & Privacy, 7(6):82–85, 2009.
Oliver Amft and Paul Lukowicz. From Backpacks to Smartphones: Past, Present, and
Future of Wearable Computers. IEEE Pervasive Computing, 8:8–13, 2009.
Melanie Anderson and Jon Serra. Mobile Devices in the Classroom – Are You Getting
It? In Proceedings of the 44th Annual Conference on Academic and Administrative
Technology Issues and Innovation in Higher Education, pages 36–40. The Association
of Small Computer Users in Education (ASCUE), 2011.
Adrienne Andrew, Yaw Anokwa, Karl Koscher, Jonathan Lester, and Gaetano Borriello.
Context to make you more aware. In Proceedings of the 27th International Confer-
ence on Distributed Computing Systems Workshops, 2007 (ICDCSW’07), pages 49–54.
IEEE Computer Society, 2007.
Koji Ara, Tomoaki Akitomi, Nobuo Sato, Satomi Tsuji, Miki Hayakawa, Yoshihiro Wak-
isaka, Norio Ohkubo, Rieko Otsuka, Fumiko Beniyama, Norihiko Moriwaki, et al.
Healthcare of an organization: using wearable sensors and feedback system for ener-
gizing workers. In Proceedings of the 16th Asia and South Pacific Design Automation
Conference, pages 567–572. IEEE Press, 2011.
Paul Baepler and Cynthia James Murdoch. Academic Analytics and Data Mining in
Higher Education. International Journal for the Scholarship of Teaching and Learning,
4(2), July 2010.
Jorge Bahamonde, Alejandro Hevia, Giselle Font, Javier Bustos-Jiménez, and Camila
Montero. Mining private information from public data: The transantiago case. Per-
vasive Computing, IEEE, 13(2):37–43, 2014.
Rebecca Balebako, Pedro G. León, Hazim Almuhimedi, Patrick Gage Kelley, Jonathan
Mugan, Alessandro Acquisti, Lorrie Faith Cranor, and Norman Sadeh. Nudging users
towards privacy on mobile devices. In ACM Workshop of the Conference on Human
Factors in Computing Systems (CHI 2011), 2011.
Albert-Lázló Barabási. Linked: How everything is connected to everything else and what
it means. Perseus Books, 2003.
45

REFERENCES 46
Albert-Lázló Barabási. The Origin of Bursts and Heavy Tails in Human Dynamics.
Nature, 435(7039):207–211, 2005.
Albert-Lázló Barabási. Bursts: The hidden pattern behind everything we do. EP Dutton,
2010.
Rebecca Barber and Mike Sharkey. Course correction: using analytics to predict course
success. In Proceedings of the 2nd International Conference on Learning Analytics
and Knowledge, pages 259–262. ACM, 2012.
Paul Baumann, Wilhelm Kleiminger, and Silvia Santini. The influence of temporal and
spatial features on the performance of next-place prediction algorithms. In Proceed-
ings of the 2013 ACM International Joint Conference on Pervasive and Ubiquitous
Computing, pages 449–458. ACM, 2013.
Arthur Baxter and Sue Hatt. Old and young mature students. painting a fuller picture.
Journal of Access and Credit Studies, 1(2):137–48, 1999.
Steve Benford, Chris Greenhalgh, Gabriella Giannachi, Brendan Walker, Joe Marshall,
and Tom Rodden. Uncomfortable interactions. In ACM Workshop of the Conference
on Human Factors in Computing Systems (CHI 2012), May 2012.
Vladlena Benson and Stephanie Morgan. Student experience and ubiquitous learning in
higher education: impact of wireless and cloud applications. Creative Education, 4:1,
2013.
Ronald A. Berk. Teaching strategies for the net generation. Transformative Dialogues:
Teaching and Learning Journal, 3(2):1–23, 2009.
Ronald A. Berk. How Do You Leverage the Latest Technologies, including Web 2.0
Tools, in Your Classroom? International Journal of Technology in Teaching and
Learning, 6(1):1–13, 2010.
Brijesh Kumar Bhardwaj and Saurabh Pal. Data mining: A prediction for performance
improvement using classification. (IJCSIS) International Journal of Computer Science
and Information Security, 9(4):136–140, April 2011.
Gerald Bieber and Christian Peter. Using physical activity for user behavior analysis.
In Proceedings of the 1st International Conference on PErvasive Technologies Related
to Assistive Environments, page 94. ACM, 2008.
Alfredo Cádiz. Desde la web a los móviles: Llevando U-Cursos a nuestros bolsillos.
Dissertation, Dept. de Computación, December 2013.
Alfredo Cádiz, Adriana Wilde, Ed Zaluska, Javier Villanueva, and Javier Bustos-
Jiménez. Participatory design of a mobile application to support classroom teaching:
the u-cursos experience. 2014.

REFERENCES 47
Jane E. Caldwell. Clickers in the Large Classroom: Current Research and Best-Practice
Tips. Journal of Cell Biology Education – Life Sciences Education (CBE-LSE), 6(1):
9–20, 2007.
Zixue Cheng, Shengguo Sun, Mizuo Kansen, Tongjun Huang, and Aiguo He. A Person-
alized Ubiquitous Education Support Environment by Comparing Learning Instruc-
tional Requirement with Learner’s Behavior. In 19th International Conference on
Advanced Information Networking and Applications, (AINA 2005), volume 2, pages
567–573. IEEE, 2005.
Shane Dawson. “Seeing” the learning community: An exploration of the development of
a resource for monitoring online student networking. British Journal of Educational
Technology, 41(5):736–752, 2010.
Manlio De Domenico, Antonio Lima, and Mirco Musolesi. Interdependence and Pre-
dictability of Human Mobility and Social Interactions. In The Nokia Mobile Data
Challenge Workshop (collocated with PERVASIVE), June 2012.
Yves-Alexandre de Montjoye, Jordi Quoidbach, Florent Robic, and Alex (Sandy) Pent-
land. Predicting personality using novel mobile phone-based metrics. In Ariel M.
Greenberg, William G. Kennedy, and Bos Nathan D., editors, Social Computing,
Behavioral-Cultural Modeling and Prediction: 6th International Conference, SBP 2013
Washington, DC, USA, April 2-5, 2013 Proceedings, volume 7812 of LNCS, pages 48–
55. Springer, 2013.
Michael Derntl. Patterns for Person-Centered E-learning. PhD thesis, University of
Vienna, 2005. http://elearn.pri.univie.ac.at/derntl/diss/diss-derntl.pdf.
Taryn Dinkelman and Claudia Martı́nez A. Investing in schooling in Chile: The role
of information about financial aid for Higher Education. Review of Economics and
Statistics, 96(2):244–257, 2014.
Alan Dix. Deconstructing experience: Pulling crackers apart. In Mark A. Blythe, Kees
Overbeeke, Andrew F. Monk, and Peter C. Wright, editors, Funology: From Usability
to Enjoyment, Human-Computer Interaction Series (Book 3). Springer, 2004.
Wen Dong, Daniel Olguin-Olguin, Benjamin Waber, Taemie Kim, and Alex Pentland.
Mapping organizational dynamics with body sensor networks. In Wearable and Im-
plantable Body Sensor Networks (BSN), 2012 9th International Conference on, pages
130–135. IEEE, 2012.
André G.C. dos Santos, João M.P. Cardoso, Diogo R. Ferreira, Pedro C. Diniz, and Paulo
Chaı́nho. Providing User Context for Mobile and Social Networking Applications.
Pervasive and Mobile Computing, 6(3):324–341, 2010.
Nathan Eagle and Alex Pentland. Reality mining: sensing complex social systems.
Personal and ubiquitous computing, 10(4):255–268, 2006.

REFERENCES 48
Nathan Eagle, Alex (Sandy) Pentland, and David Lazer. Inferring Friendship Network
Structure by Using Mobile Phone Data. Proceedings of the National Academy of
Sciences (PNAS), 106(36):15274, 2009.
Tracy Epton, Paul Norman, Paschal Sheeran, Peter R Harris, Thomas L Webb, Fabio
Ciravegna, Alan Brennan, Petra Meier, Steven A Julious, Declan Naughton, et al. A
theory-based online health behavior intervention for new university students: study
protocol. BMC public health, 13(1):107, 2013.
Manuel Estrems, Fernando Cerdán, Diego Garcı́a, Horacio T. Sánchez, and Patricio
Franco. The Application of PDAs and Smartphones in the Classroom as Instruments
for Improvement of Learning Monitoring. Materials Science Forum, 625:113–121,
2009.
Brianna S Fjeldsoe, Alison L Marshall, and Yvette D Miller. Behavior change inter-
ventions delivered by mobile telephone short-message service. American journal of
preventive medicine, 36(2):165–173, 2009.
Brian J Fogg. Persuasive Technology: Using computers to change what we think and do.
Morgan Kaufmann Publishers, 2003.
Brian J Fogg. Creating persuasive technologies: an eight-step design process. In Per-
suasive, page 44, 2009.
Katie Fraser, Tom Rodden, and Claire O’Malley. Trust, Privacy and Relationships in
‘Pervasive Education’: Families’ Views on Homework and Technologies. In Pervasive,
number 4480 in LNCS, pages 180–197. Springer, 2007.
William J. Frawley, Gregory Piatetsky-Shapiro, and Christopher J. Matheus. Knowledge
discovery in databases: An overview. AI Magazine, 13(3):57, 1992.
Malcolm Gladwell. The Tipping Point: How little things can make a big difference.
Little, Brown and Company, 2000.
Nenad Gligoric, Ana Uzelac, and Srdjan Krco. Smart classroom: Real-time feedback on
lecture quality. In Pervasive Computing and Communications Workshops (PERCOM
Workshops), 2012 IEEE International Conference on, pages 391–394. IEEE, 2012.
Joseph G Glynn, Paul L Sauer, and Thomas E Miller. Signaling student retention with
prematriculation data. Journal of Student Affairs Research and Practice (NASPA,
National Association of Student Personnel Administrators), 41(1), December 2003.
Great Britain. Parliament. House of Lords. Science and Technology Committee - Sec-
ond Report Behaviour Change. Technical report, Great Britain and Parliament and
“House of Commons”, July 2011. Chapter 2: Definitions, Categorisation and the
Ethics of Behaviour Change Interventions.

REFERENCES 49
William G. Griswold, Patricia Shanahan, Steven W. Brown, Robert Boyer, Matt
Ratto, R.Benjamin Shapiro, and Tan Minh Truong. ActiveCampus: Experiments
in Community-Oriented Ubiquitous Computing. Computer, 37(10):73–81, 2004.
Ralph Gross and Alessandro Acquisti. Information Revelation and Privacy in Online So-
cial Networks. In Proceedings of the 2005 ACM workshop on Privacy in the electronic
society, pages 71–80, 2005.
Erica Gunn. Using clickers to collect formative feedback on teaching: A tool for faculty
development. International Journal for the Scholarship of Teaching and Learning, 8
(1):11, 2014.
Sajanee Halko and Julie A Kientz. Personality and persuasive technology: An ex-
ploratory study on health-promoting mobile applications. In Persuasive technology,
pages 150–161. Springer, 2010.
Ellen Johanna Helsper and Rebecca Eynon. Digital Natives: Where is the Evidence?
British Educational Research Journal, 36(3):503–520, 2010.
Samuli Hemminki, Petteri Nurmi, and Sasu Tarkoma. Accelerometer-based transporta-
tion mode detection on smartphones. In Proceedings of the 11th ACM Conference on
Embedded Networked Sensor Systems, page 13. ACM, 2013a.
Samuli Hemminki, Kai Zhao, Aaron Yi Ding, Martti Rannanjärvi, Sasu Tarkoma, and
Petteri Nurmi. Cosense: a collaborative sensing platform for mobile devices. In
Proceedings of the 11th ACM Conference on Embedded Networked Sensor Systems,
page 34. ACM, 2013b.
Nicky Hockly. The digital generation. ELT Journal, 65(3):322–325, 2011.
Gwyneth Hughes. Diversity, Identity and Belonging in e-Learning Communities: Some
Theories and Paradoxes. Teaching in Higher Education, 12(5-6):709–720, 2007.
Hayley Hung, Gwenn Englebienne, and Jeroen Kools. Classifying Social Actions with a
Single Accelerometer. In Proceedings of the International Joint Conference on Perva-
sive and Ubiquitous Computing (UbiComp 2013), pages 207–210. ACM, 2013.
Duy Tâm Gilles Huynh. Human Activity Recognition with Wearable Sensors. PhD thesis,
2008. Technische Universität Darmstadt. http://tuprints.ulb.tu-darmstadt.de/
1132/.
Duy Tâm Gilles Huynh and Bernt Schiele. Analyzing Features for Activity Recognition.
In Proceedings of the joint Conference on Smart Objects and Ambient Intelligence:
Innovative Context-Aware Services: Usages and Technologies, pages 159–163. ACM,
2005.

REFERENCES 50
Gwo-Jen Hwang and Chin-Chung Tsai. Research Trends in Mobile and Ubiquitous
Learning: A Review of Publications in Selected Journals from 2001 to 2010. British
Journal of Educational Technology, 42(4):E65–E70, 2011.
Gwo-Jen Hwang, Chin-Chung Tsai, and Stephen J.H. Yang. Criteria, Strategies and
Research Issues of Context-Aware Ubiquitous Learning. Educational Technology &
Society, 11(2):81–91, 2008.
Paul Hyman. In the year of disruptive education. Communications of the ACM, 55(12):
20–22, 2012.
Christopher Jones and Binhui Shao. The Net Generation and Digital Natives – Implica-
tions for Higher Education: A literature review commissioned by the Higher Education
Academy. Higher Education Academy, 2011.
David Thomas Jones. An Information Systems Design Theory for e-
Learning. PhD thesis, Australian National University, February 2011.
http://davidtjones.files.wordpress.com/2011/05/allthesisfinalsubmission.pdf.
David Kember. A Reconceptualisation of the Research into University Academics’ Con-
ceptions of Teaching. Learning and instruction, 7(3):255–275, 1997.
Gregor Kennedy, Terry Judd, Barney Dalgarno, and Jenny Waycott. Beyond natives
and immigrants: exploring types of net generation students. Journal of Computer
Assisted Learning, 26(5):332–343, 2010.
Kathy Kenwright. Clickers in the classroom. TechTrends, 53(1):74–77, 2009.
Asad Masood Khattak, Phan Tran Ho Truc, Le Xuan Hung, La The Vinhn, Viet-
Hung Dang, Donghai Guan, Zeeshan Pervez, Manhyung Han, Sungyoung Lee, and
Young-Koo Lee. Towards smart homes using low level sensory data. Sensors, 11(12):
11581–11604, 2011.
Predrag Klasnja, Sunny Consolvo, and Wanda Pratt. How to evaluate technologies for
health behavior change in HCI research. In Proceedings of the SIGCHI Conference on
Human Factors in Computing Systems (CHI), pages 3063–3072. ACM, 2011.
Teemu H. Laine and Mike S. Joy. Survey on Context-Aware Pervasive Learning En-
vironments. International Journal of Interactive Mobile Technologies (iJIM), 3(1):
70–76 and references therein, 2009.
Teemu Henrikki Laine, Mikko Vinni, Carolina Islas Sedano, and Mike Joy. On Designing
a Pervasive Mobile Learning Platform. ALT-J, Research in Learning Technology, 18
(1):3–17, March 2010.
Nicholas Lane, Emiliano Miluzzo, Hong Lu, Daniel Peebles, Tanzeem Choudhury, and
Andrew Campbell. A Survey of Mobile Phone Sensing. IEEE Communications Mag-
azine, 48(9):140–150, 2010.

REFERENCES 51
Neal Lathia, Veljko Pejovic, Kiran K Rachuri, Cecilia Mascolo, Mirco Musolesi, and
Peter J Rentfrow. Smartphones for large-scale behaviour change interventions. IEEE
Pervasive Computing, 12(3):66–73, 2013.
Sian Lun Lau. Towards a user-centric context aware system: empowering users
through activity recognition using a smartphone as an unobtrusive device. PhD the-
sis, Kassel Universität, Germany, 2012. http://books.google.co.uk/books?id=
mmfNbONYIEoC.
James Manyika, Michael Chui, Brad Brown, Jacques Bughin, Richard Dobbs, Charles
Roxburgh, and Angela H Byers. Big data: The next frontier for innovation, competi-
tion, and productivity. McKinsey Global Institute, June 2011.
Lars Müller, Verónica Rivera-Pelayo, and Stephan Heuer. Persuasion and reflective
learning: closing the feedback loop. In M. Bang and E.L. Ragnemalm, editors, Persua-
sive Technology. Design for Health and Safety, volume 7284 of LNCS, pages 133–144.
Springer, 2012.
David Nicholas, Ian Rowlands, and Paul Huntington. information behaviour of the
researcher of the future. Joint Information Systems Committee (JISC), UCL, SLAIS,
January 2008.
Kieron O’Hara. Narcissus to a man: Lifelogging, technology and the normativity of
truth. In 2nd Annual SenseCam Symposium, 2010.
Clare Owens, David E. Millard, and Andrew Stanford-Clark. Towards a Social Fabric
for Pervasive Assistive Environments. In Proceedings of the IEEE 2nd International
Conference on PErvasive Technologies Related to Assistive Environments (PETRA).
IEEE, 2009.
John Palfrey and Urs Gasser. Born Digital: Understanding the First Generation of
Digital Natives. Basic Books (AZ), 2010.
Alex Sandy Pentland. To Signal Is Human: Real-time data mining unmasks the power of
imitation, kith and charisma in our face-to-face social networks. American Scientist,
pages 204–211, 2010.
Christoph Pimmer, Sebastian Linxen, Urs Gröhbiel, Anil Kumar Jha, and Günter Burg.
Mobile learning in resource-constrained environments: A case study of medical edu-
cation. Medical teacher, 35(5):e1157–e1165, 2013.
Marc Prensky. Digital Natives, Digital Immigrants Part 1. On the Horizon, 9(5):1–6,
2001a.
Marc Prensky. Digital Natives, Digital Immigrants Part 2: Do They Really Think
Differently? On the Horizon, 9(6):1–9, 2001b.

REFERENCES 52
Everett M Rogers. Diffusion of innovations. Simon and Schuster, 1962.
Y. Rogers, S. Price, G. Fitzpatrick, R. Fleck, E. Harris, H. Smith, C. Randell, H. Muller,
C. O’Malley, D. Stanton, M. Thompson, and M. Weal. Ambient Wood: Designing
New Forms of Digital Augmentation for Learning Outdoors. In Proceedings of the
2004 conference on Interaction design and children: building a community, pages 3–
10. ACM, 2004.
Yvonne Rogers, Sarah Price, Cliff Randell, Danae Stanton Fraser, Mark Weal, and Geral-
dine Fitzpatrick. Ubi-Learning Integrates Indoor and Outdoor Experiences. Commu-
nications of the ACM, 48(1):55–59, 2005.
Cristóbal Romero and Sebastián Ventura. Educational data mining: a review of the
state of the art. Systems, Man, and Cybernetics, Part C: Applications and Reviews,
IEEE Transactions on, 40(6):601–618, 2010.
Carolyn Penstein Rosé, Ryan Carlson, Diyi Yang, Miaomiao Wen, Lauren Resnick, Pam
Goldman, and Jennifer Sherer. Social factors that contribute to attrition in moocs.
In Proceedings of the first ACM conference on Learning@ scale conference, pages 197–
198. ACM, 2014.
Neil Rubens, Dain Kaplan, and Toshio Okamoto. E-learning 3.0: anyone, anywhere,
anytime, and ai. In New Horizons in Web Based Learning, pages 171–180. Springer,
2014.
Dairazalia Sanchez-Cortes, Oya Aran, Marianne Schmid Mast, and Daniel Gatica-Perez.
A nonverbal behavior approach to identify emergent leaders in small groups. Multi-
media, IEEE Transactions on, 14(3):816–832, 2012.
Farhana Sarker. Linked Data Technologies to Support Higher Education Challenges: Stu-
dent Retention, Progression and Completion. PhD thesis, Electronics and Computer
Science, University of Southampton, 2014. Manuscript received from its author.
Albrecht Schmidt, Michael Beigl, and Hans-W. Gellersen. There is more to Context
than Location. Computers & Graphics, 23(6):893–901, 1999.
Mike Sharkey. Academic analytics landscape at the university of phoenix. In Proceedings
of the 1st International Conference on Learning Analytics and Knowledge, pages 122–
126. ACM, 2011.
Ashley Smith, Wendy Hall, Hugh Glaser, and Leslie A Carr. Towards Truly Ubiquitous
Life Annotation. In Proceedings of the Web Science Conference. Koblenz, Germany,
2011.
Ashley Smith, Kieron O’Hara, and Paul Lewis. Visualising the Past: Annotating a Life
with Linked Open Data. In Memories for Life Colloquium. London, UK: The British
Library, 2006.

REFERENCES 53
Judith Smith. Mature learners: A synthesis of research. Higher Education Academy,
2008.
Chaoming Song, Zehui Qu, Nicholas Blumm, and Albert-Lázló Barabási. Limits of
Predictability in Human Mobility. Science, 327(5968):1018–1021, 2010.
Mani Srivastava, Tarek Abdelzaher, and Boleslaw Szymanski. Human-centric sensing.
Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engi-
neering Sciences, 370(1958):176–197, 2012.
Pei-Chen Sun, Ray J Tsai, Glenn Finger, Yueh-Yang Chen, and Dowming Yeh. What
drives a successful e-learning? an empirical investigation of the critical factors influ-
encing learner satisfaction. Computers & Education, 50(4):1183–1202, 2008.
Richard Thaler and Cass Sunstein. Nudge: Improving Decisions about Health, Wealth,
and Happiness. Yale University Press, 2008.
Jeffrey Travers and Stanley Milgram. An experimental study of the small world problem.
Sociometry, pages 425–443, 1969.
Sherry Turkle. Always-On/Always-On-You: The Tethered Self. Handbook of Mobile
Communication Studies and Social Change, pages 121–137, 2008.
Alexei Vázquez, João Gama Oliveira Oliveira, Zoltán Dezsö, Kwang-Il Goh, Imre Kon-
dor, and Albert-Lázló. Barabási. Modeling bursts and heavy tails in human dynamics.
Physical Review E, 73(3):036127, 2008.
L.M. Wallace, K.E. Brown, and S. Hilton. Planning for, implementing and assessing the
impact of health promotion and behaviour change interventions: a way forward for
health psychologists. Health Psychology Review, 8(1):8–33, 2014.
Richard Waller. ‘I don’t feel like ‘a student’, I feel like ‘me’!’: the over-simplification
of mature learners’ experience(s). Research in Post-Compulsory Education, 11(1):
115–130, 2006.
Roy Want, Andy Hopper, Veronica Falcao, and Jonathan Gibbons. The active badge
location system. ACM Transactions on Information Systems (TOIS), 10(1):91–102,
1992.
Jun-ichiro Watanabe, Marina Fujita, Kazuo Yano, Hideo Kanesaka, and Tomoyuki
Hasegawa. Resting time activeness determines team performance in call centers. Hu-
man Journal, 1(4):193–204, 2012.
Jun-Ichiro Watanabe, Saki Matsuda, and Kazuo Yano. Using wearable sensor badges to
improve scholastic performance. In Adjunct Proceedings of the 2013 ACM conference
on Pervasive and Ubiquitous Computing, pages 139–142. ACM, 2013.

REFERENCES 54
Mark J Weal, Charlie Hargood, Danius T Michaelides, Leanne Morrison, and Lucy
Yardley. Making online behavioural interventions mobile. In Digital Research 2012,
September 2012.
Mark Weiser. The Computer for the 21st Century. ACM SIGMOBILE Mobile Computing
and Communications Review, 3(3):3–11, 1999.
Miaomiao Wen, Diyi Yang, and Carolyn Penstein Rosé. Linguistic reflections of stu-
dent engagement in massive open online courses. In Proceedings of the International
Conference on Weblogs and Social Media (poster), 2014.
David S. White, Lynn Silipigni Connaway, Donna Lanclos, Alison Le Cornu, and Erin
Hood. Digital visitors and residents: Progress report. Joint Information Systems
Committee (JISC), University of Oxford, OCLC, University of North Carolina, June
2012.
Adriana Wilde. Can pervasive computing make you happy? In Google EMEA Scholar-
ships Retreat, Googleplex, Zürich, Switzerland, July 2013.
Adriana Wilde. Adapting to class sizes: what feedback fits best? In Improving stu-
dent satisfaction with assessment and feedback – one day conference, University of
Southampton, February 2014.
Adriana Wilde, Richard Oliver, and Ed Zaluska. Developing a low-cost general-purpose
device for the Internet of Things. In 7th International Conference on Sensing Tech-
nology, Wellington, New Zealand, December 2013a.
Adriana Wilde, Andrew Paverd, Oliver Gasser, and Moira McGregor. EINS PRIME:
Perception and Realisation of Information privacy using Measurements and Ethnog-
raphy. In Towards Meaningful: Perspectives on Online Consent @ Digital Economy
Conference 2013: Open Digital, Salford, Manchester, UK, November 2013b.
Adriana Wilde and Ed Zaluska. Revisiting activity theory within the Internet of Things.
In 1st International Workshop on Internet Science and Web Science Synergies, Paris,
France, May 2013.
Adriana Wilde, Ed Zaluska, and Hugh Davis. ‘Happiness’: Can pervasive computing
assist students to achieve success? In Adjunct Proceedings of the 2013 ACM conference
on Pervasive and Ubiquitous Computing, ETH, Zürich, Switzerland, September 2013c.
ACM.
Adriana Wilde, Ed Zaluska, and Hugh Davis. “Happiness” (or Student Success and
Pervasive Computing). In Poster Session of the UBICOMP Doctoral School, ETH,
Zürich, Switzerland, September 2013d.

REFERENCES 55
Lynn Wu, Benjamin Waber, Sinan Aral, Erik Brynjolfsson, and Alex Sandy Pentland.
Mining face-to-face interaction networks using sociometric badges: Predicting produc-
tivity in an it configuration task. The Winter Conference on Business Intelligence,
2008.
Diyi Yang, Tanmay Sinha, David Adamson, and Carolyn Penstein Rosé. Turn on,
tune in, drop out: Anticipating student dropouts in massive open online courses. In
Proceedings of the 2013 NIPS Data-Driven Education Workshop, 2013.
Stephen J.H. Yang. Context Aware Ubiquitous Learning Environments for Peer-to-Peer
Collaborative Learning. Journal of Educational Technology and Society, 9(1):188,
2006.

Appendix A
Beyond this thesis
The original motivation for this thesis was to use context-aware pervasive computing to
support positive behaviours of Higher Education students to assist them to succeed. This
support could come in a number of ways, but I was particularly interested in enabling
reflection as a necessary step towards behaviour change. Soon enough, during the course
of my investigation, it became clear that learning analytics are essential to identify those
factors (not only behavioural ones, but also the conditioning factors) determining their
academic success. This in itself is a worthy research topic, and I have elected to focus
on it. However, the “big picture” motivation remains: how to help students reflect on
their behaviour?
A.1 How to help students reflect on their behaviour?
As supported by my literature review in Chapter 2, learning can be supported using
pervasive computing. Any knowledge about existing behaviours, alongside with those
of their peers as a whole, as well as that of “successful students” would be very valuable
to inform students’ learning. Triggered by contextual clues, positive “nudges” could be
advantageous to aspiring students to better achieve their goals of academic success.
In the context of behavioural interventions, the term nudge, as used by Balebako
et al. (2011) and Acquisti (2009) was first introduced by Thaler and Sunstein (2008)
to describe “any aspect of the choice architecture that alters people’s behaviour in a
predictable way without forbidding any options or significantly changing their economic
incentives.” By choice architecture these authors refer to the environment (either social
or physical) in which individuals make choices. There is an element of low-awareness on
the part of the individual of such an architecture, so the individuals are still exercising
their free will when making choices, however such a choice might have been different
were it not for the intervention. A taxonomy of different types of “behaviour change
56

Appendix A Beyond this thesis 57
interventions” (Great Britain. Parliament. House of Lords, 2011), including examples,
is presented in Table A.1. In this table, highlighted, are the nudges that I propose to
implement using context-aware pervasive computing in Higher Education. These fall all
within the last intervention category: “Guide and enable choice”, in particular:
• Persuasion: By encouraging students to engage in good study habits and be-
haviours.
• Provision of information: By raising awareness of own behaviour via a person-
alised smartphone app.
• Use of social norms and salience: By providing information about what suc-
cessful students are doing.
It is possible, therefore, to “nudge” (in Thaler and Sunstein’s sense) students into
good habits and behaviours using pervasive computing. However, this is not an easy task.
A multiplicity of sensor modalities and sources of academic data might prove challenging
to integrate. The use of smartphones to this end, whilst ideal due to their continuous
use amongst some “digital natives”, relies heavily on the assumption of overcoming
many technical challenges such as the independence of the orientation of the device for
correct classification and the issue of battery drain (due to the high energy consumption
associated with sensors operating continuously). Another difficulty is inherent to the
nature of the question itself: what would be the measure of an improvement in learning?
I could look for changes in levels of engagement at both ends of the spectrum. For
example, as Griswold et al. (2004) suggests, “are more students pursuing independent
research later in their studies, or are fewer students dropping classes?” In other words,
are the stronger students being better stretched, and weaker students better supported?
Such outcomes would not necessarily be apparent in measures such as their examination
marks.
An area of research in need of exploration has been successfully identified in this
upgrade report, which combines an extensive range of contextual information in order
to understand students’ behaviour (e.g. context gathered via their smartphones, as well
as data from their educational institutions). I have also identified that this analysis
can be potentially used to increase students chances of academic success, by facilitating
reflection, and thereby encouraging behaviour change. This is already possible. The
knowledge that human behaviour is somewhat predictable given our history and that of
our peers could be used to provide “nudges” to guide and enable choice towards effective
behavioural interventions.
I contend that my research is foundational to enable further work on digital be-
havioural interventions on Higher Education students, as by identifying the measurable
factors influencing academic success, these can be monitored, and used to learn about

Appendix
A
Beyond
this
thesis
58
Table A.1: Table of interventions. (Adapted from Great Britain. Parliament. House of Lords (2011).)
Regulation of the
individual
Financial measures
directed at the
individual
Non-regulatory, non-financial measures in relation to the individual
Choice Architecture (“Nudges”)
Interv.category
Guide and enable choice
Eliminate
choice
Restrict
choice
Financial
disincentives
Financial
incentives
Non-
financial
incen-
tives and
disincentives
Persuasion Provision of
information
Changes
to physical
environment
Changes to
the default
policy
Use of social
norms and
salience
Examples
of
interventions
Prohibiting
goods or
services (e.g.
banning
certain
drugs)
Restricting
the options
available to
individuals
(e.g. out-
lawing
smoking
in public
places)
Fiscal poli-
cies to make
behaviours
more costly
(e.g. tax on
tobacco)
Fiscal poli-
cies to make
behaviours
financially
beneficial
(e.g. tax
breaks on
the purchase
of bicycles)
Policies to
reward or
penalise
behaviours
(e.g. time
off work to
volunteer)
Persuading
individuals
using
argument
(e.g. GPs
persuading
people to
drink less)
Providing
information
in leaflets
(e.g. show-
ing carbon
usage of
household
appliances)
Altering the
environment
(e.g. traffic
calming
measures)
Changing
the default
option (e.g.
requiring
people to
opt out
rather than
opt in to
organ dona-
tion)
Providing
information
about what
others are
doing (e.g.
the energy
usage of a
a household
against the
rest of the
street)

Appendix A Beyond this thesis 59
the behaviour which could in turn be used to help students reflect and change as they
receive suitable, personalised feedback.
Based on the current trend of increasingly widespread use of smartphones, these are
potentially useful in delivering digital behavioural interventions effectively. As Figure
2.6 (in page 16) shows, smartphones can be used not only for the delivery but also for
the monitoring (measuring additional factors) and learning of the behaviour. Measur-
ing factors additional to those available through learning management systems could
contribute in forming a broader, more complex, model of learning behaviour. Factors
that then could be explored include rest (or sleeping patterns), levels of noise whilst
studying, physical activity and mobility.
Furthermore, given that Higher Education students today have unprecedented ac-
cess to digital technology, I considered that many may well be already receptive for the
use of new technology to better achieve their goal of academic success. In fact, I have
already tested this contention through two surveys, one of 162 participants in the UK,
and the other of 124 participants in Chile (specifically, University of Chile students). As
shown in Chapter 4, these surveys suggest that most students do not object to enabling
their smartphones to be used as tools for their academic success, though many respon-
dents reported various concerns. Concerns tended to refer to the feedback provided via
smartphones, specifically regarding locus of control and privacy considerations which
were, paradoxically, often in disagreement with their reported current practices. A way
to alleviate these reservations is by giving users complete control of their own data and
by adopting strong policies on data anonymity.
As a final remark, my current research is also foundational for future extensions of U-
Cursos mobile, or a similar learning management system which would provide relevant
“nudges” in the form of granular pushes, based on information known about the user. It
would be of interest to set up an experiment in which the capabilities of such a platform
are tested in terms of how effective it is in encouraging reflection towards behaviour
change. However, given the time and resources restrictions, this experiment is out of
scope.

Appendix B
Predictability of human
behaviour
In Linked, Barabási (2003) made network science accessible by explaining the mecha-
nisms by which scale-free networks are formed and maintained, with some nodes (“hubs”)
having many more connections than others, resulting in the whole network exhibiting a
power-law distribution1 of the number of links per node. A strong message of this book
is that people connect to each other via scale-free networks. One natural implication of
this message is that, if the connectivity can be translated into a social behaviour (the
degree of “connectedness”), there is such a great range of social behaviours that might
make generalisations difficult. Whilst Gladwell (2000, Ch. 2: The Law of the Few) goes
a step further by using the term connectors to refer to those highly connected individu-
als, who, alongside mavens and salesmen2 play an important role in the dissemination
of knowledge, practices and behaviours.
A quantitative understanding of human behaviour is of interest since individual hu-
man actions drive the dynamics of most social, economic and technological phenomena
(Barabási, 2005). According to this influential article, human behavioural patterns are
affected by decision-based queuing processes: if people complete tasks based on some
perceived priority, the timing of these tasks will be heavy tailed (with most tasks be-
ing quickly performed whilst a few experience very long waiting times). Challenging
1
In other words, very few nodes having the majority of the links, whilst the majority of the nodes
have very few links. Power-law distributions follow a probability density function with parameters k
and α:
f(x) =

αkα
x−α−1
x ≥ k
0 otherwise
(http://www.wolframalpha.com/input/?i=power+law+distribution).
2
Drawing conclusions from earlier work conducted by Travers and Milgram (1969), Gladwell (2000)
presents a typology of agents of change at the moment of critical mass, from which epidemic-like diffusion
starts. connectors know a great number of people in various circles, mavens accumulate knowledge and
share it with others, and salesmen who persuade others, even unintentionally.
60

Appendix B Predictability of human behaviour 61
widely accepted models of human behaviour and dynamics, which assume randomness
over time, Barabási and collaborators evidence that many human activities follow non-
Poisson statistics3 over time (Song et al., 2010; Vázquez et al., 2008). Human activities
are instead characterized by bursts of events in quick succession separated by long peri-
ods of inactivity, indicating therefore a certain degree of predictability, which applies to
a great range of human activity, such as letter based communications and e-mail, web
browsing, library visits and stock trading.
In Bursts, Barabási (2010) argues convincingly that, despite significant differences
in mobility patterns present in the general population, truly spontaneous individuals
are very rarely found. Barabási and collaborators found that human behaviour is 93%
predictable. In order to arrive at such a result, these researchers explored the pre-
dictability of human dynamics by studing human mobility. Their research focus was on
the fundamental limits of predictability of human mobility in particular, using a large,
complex dataset containing a three-month-long record of mobile phone data, collected
for billing purposes and anonymised at source. These findings have been corroborated
by studies such as that by De Domenico et al. (2012) who were able to predict with
increased accuracy a given person’s next location with the knowledge of their peers’
mobility. Additionally, Eagle et al. (2009) were able to observe particular behaviours by
analysing mobile phone data, indicating some predictability of human behaviour in the
context of friendship networks too.
3
In Poisson processes: 1. the number of occurrences in non-overlapping intervals are independent; 2.
the probability of exactly one occurrence in a sufficiently small interval h ≡ 1/n is P = νh ≡ ν/n where ν
is the probability of one occurrence and n is the number of trials; 3. the probability of two simultaneous
occurrences is negligible. For a very large the number of trials becoming, the resulting distribution is
called a Poisson distribution. (http://www.wolframalpha.com/input/?i=poisson+process).

Appendix C
Survey questions
Smartphone use by students in Higher Education
In this study we are seeking to identify your current use of smartphones as well
as establish early acceptability of a future application intended to support students in
Higher Education.
This survey will take approximately 10 minutes of your time, there are no particular
risks associated with your participation, and you can withdraw at anytime (even after
finishing it). All data collected is anonymous.
You have been invited to complete this survey because you are a student in a Higher
Education Institution and you are over 18 years old.
Please note that by consenting to take part you are confirming your eligibility.
Ethics reference number: ERGO/FoPSE/7447
O Please tick (check) this box to confirm your eligibility and to indicate that you
consent to taking part in this survey. Click here to start this survey
1. Smartphone ownership
(a) Do you have a smartphone?
• Yes
• No, but I intend to get one during the next academic year
• No, and I do not intend to
(b) Which brand is your (current) smartphone? (Only shown if 1(a) was answered‘Yes’)
• Apple
• Blackberry
• HTC
62

Appendix C Survey questions 63
• LG
• Motorola
• Nokia
• Samsung
• Sony
• Toshiba
• Other
2. You and your smartphone (Only shown if 1(a) was answered‘Yes’)
Reflecting upon your smartphone use in the last term, how often did you perform
each of the following activities?
• Make or receive phone calls
• Send or receive texts
• Send or receive photos or videos
• Take photos or record videos
• Play games or music
• Play videos (other than games)
• Use social networking websites
• Blog
• Read blogs
• Read news (other than from blogs and social networks)
• Compare products or services
• Purchase products or services
• Search for a job
• Collaborate with others for coursework
• Use calendar or reminders
• Play podcasts
• Web browsing for coursework or study
• General web browsing (other than above)
For each of the categories above, the options are:
• Several times a day,
• At least once a day,
• Several times a week,
• At least once a week,
• Less often than once a week,
• Never

3. Your smartphone and your studies (Only shown if 1(a) was answered‘Yes’)
(a) In a typical weekday during term time, do you use your smartphone most
often for your studies, for personal reasons (including work outside your stud-
ies), or somewhere in between?1
Most often for my studies ←→ Most often for personal reasons
(b) In a typical weekend (and days outside of term time), do you use your phone
most often for your studies, for personal reasons, or somewhere in between?
Most often for my studies ←→ Most often for personal reasons
(c) Overall, do you consider your phone use as an aid towards your personal goals
during your time at university, as a barrier or something in between?
A help ←→ A barrier
(d) Do you consider your phone as an aid towards your academic success, a
barrier, or something in between?
A help ←→ A barrier
4. Future use of your smartphone
(Not shown if 1(a) was answered ‘No, and I do not intend to’)
(a) How desirable are the following features of an application intended to support
you in your studies?
• “Checks you in” when entering learning spaces
• Allows you to keep a private log of your activities
• Keeps a record of your (physical) activity level in an automatic manner
• Gives you feedback on your behaviour
• Feedback on how your peers are doing as a whole in similar tasks
• Gives you feedback on the amount of interaction with others over a period
of time
For each of the categories above, the options are:
• Very desirable
• Somewhat desirable
• Not desirable at all
(b) Do any of the potential applications described above cause you any concern?
Which ones? Why? Ample space for input was provided
5. About you (Shown to all participants)
(a) When it comes to adopting new technology, to which of the following groups
would you say you probably belong?
1
Note: slider bars were offered in the online survey in place of the ←→ symbol.

• Innovators – the ”first” to adopt an innovation, with financial liquidity
to allow for the risk of technology failure.
• Early Adopters – realise judicious choices in adopting an innovation.
• Early Majority – adopt an innovation later often through influential con-
tact with early adopters.
• Late Majority – skeptical individuals who adopt an innovation after it
has been accepted by the majority.
• ’Laggard’ – the last to adopt an innovation, have very little opinion lead-
ership. Accept innovation after its establishment has driven previous
approaches into obsolescence.
• Do not know
(b) How old are you? Please select
• 18–20
• 21–24
• 25–29
• 30–39
• 40–49
• 50 or older
(c) Are you a part-time or a full-time student?
• Part-time
• Full-time
(d) Which of the following best describes your current studies?
• 1st year at an undergraduate level programme (e.g. BS BSc BEng)
• 2nd year at undergraduate level
• 3rd year at undergraduate level
• Postgraduate qualification (e.g. PGDip PGCert PGCE GTP)
• Master level programme (e.g. MSc Eng MA MPhil Mres MMus MBA
LLM)
• 1st year in a Doctorate programme (e.g. PhD EngD DBA DClinP)
• 2nd year or above in your Doctorate
(e) Please indicate in which discipline Space for input was provided
(f) In which country are you based during term-time?
• United Kingdom
• Other. Especifically which country? Space for input was provided

Appendix D
A word cloud of concerns
Figure D.1: Word cloud of participants’ answers to the question “Do any of the
potential applications described cause you any concern? Which ones? Why?”.
66

Appendix D A word cloud of concerns 67
Figure D.1 shows a word cloud of participants’ answers to the question “Do any of the
potential applications described cause you any concern? Which ones? Why?”. Answers
were aggregated so that “No”, “Nope”, and “N/A” counted as “None”. Other common
English words were removed before the word tag was generated. As it is common practice
in the generation of word clouds, high-frequency words in English language were removed
alongside some others not relevant in the context of the question.
The words removed from the answers to the open ended question (question 4(b)) for
the word-cloud generation include high-frequency words as well as several considered ir-
relevant for the discussion. These are presented in the order of the frequency in the text
combining all the responses from participants: “I”, “to”, “the”, “of”, “a”, “my”, “be”,
“on”, “in” (except when part of “checks you in”), “and”, “that”, “for”, “is”, “are”, “not”,
“it”, “how”, “would”, “doing”, “don’t”, “would”, “as”, “with”, “could”, “me”, “about”,
“what”, “or”, “your”, “do”, “any”, “if”, “but”, “an”, “they”, “this”, “can”, “all”,
“from”, “when”, “really”, “have”, “them”, “will”, “than”, “like”, “I’m”, “am”, “so”,
“you” (except when part of “checks you in”), “one”, “these”, “by”, “at”, “see”, “whole”,
“also”, “own”, “too”, “might”, “may”, “which”, “rather”, “being”, “such”, “things”,
“thing”, “try”, “very”, “some”, “just”, “their”, ‘’bit”, “bits”, “get”, “there”, “in-
volve”, “only”, “most”, “similar”, “ways”, “way”, “was”, “amount”, “quickly”, “able”,
“should”, “even”, “around”, “over”, “something”, “related”, “apart”, “big” (except
when in “Big Brother”), “up” (except after “signing”), “look”, “much”, “has”, “be-
cause”, “cause”, “actually”, “which”, “sure”, “I’d”, “I’ve”, “it’s”, “we’re”, “here”, “go”,
“already”, “sorry”, “anyway”, “else”, “first”, “barely”, “didn’t”, “wouldn’t”, “let’s”,
“don’t”, “mention”, “pieces”, “need”, “many”, “mostly”, “essentially”, “especially”,
“extremely”, “every”, “taking”, “however”, “respect”, “these”, “those”, “e.g.”, “in-
stead”, “proper”, “new”, “body”, “incredibly”.
Certain word sequences, such as “physical activity”, “checks you in”, “higher ed-
ucation” and “big brother”, were kept, as these words are especially meaningful when
together. Additionally, some answers were aggregated so that “No”, “Nope”, “-” and
“N/A” counted as “None” for the word cloud generator. Other words were aggregated
using stemming rules (e.g. plural and singular noun of a given word were counted as
the same word; “checks you in”, “check you in”, and “checking in”, were aggregated as
“checks you in”; “anonymised”, “anonymous” and “anonymising” as “anonymous”).

Appendix E
The U-Cursos experience
The following is a full reprint of the paper:
Alfredo Cádiz, Adriana Wilde, Ed Zaluska, Javier Villanueva and Javier Bustos-
Jiménez (2014) “Participatory design of a mobile application to support classroom teach-
ing: the U-cursos experience”. Submitted to MobileCHI’14.
68

Participatory design of a mobile
application to support classroom
teaching: the U-cursos experience
Alfredo Cádiz
Universidad de Chile
Depto. de Computación
Santiago, Chile
acadiz@gmail.com
Javier Bustos-Jiménez
NIC Chile Research Labs
Santiago, Chile
jbustos@niclabs.cl
Adriana Wilde
Electronics and Computer
Science
University of Southampton
Southampton, United Kingdom
agw106@ecs.soton.ac.uk
Ed Zaluska
Electronics and Computer
Science
University of Southampton
Southampton, United Kingdom
ejz@ecs.soton.ac.uk
Javier Villanueva
Área de Infotecnologı́as (ADI)
Universidad de Chile
Santiago, Chile
javier@villanueva.cl
Copyright is held by the author/owner(s).
MobileCHI’14, September 23–26, 2014, Toronto, Canada.
ACM 978-1-XXXX-XXXX-X/XX/XX.
Abstract
Learning Management Systems (LMS) are widely used to
support students, for example to complement classroom
teaching by providing learning materials and fostering
discussion. LMS research has concentrated on their
educational benefits and not on their design. Furthermore,
LMS development are often driven by a ‘top-down’ (rather
than participatory) design. U-Cursos is a successful
web-based LMS that supports classroom teaching, though
it is not yet been widely accessed through mobile devices.
Also, during the end-of-term assessments period there is
an increased access the platform, explained by users’ need
for timely information updates whilst under stress and
uncertainty. We surveyed over 4,000 users and studied
usage statistics to define key requirements for a mobile
version. These requirements led the design of a mobile
U-Cursos client to improve access and reduce uncertainty
by using statistic and participatory information.
Author Keywords
Participatory design, learning management systems,
mobile development requirements.
ACM Classification Keywords
D.2.1 [Software Engineering]:
Requirements/Specifications; K.3.1 [Computer Uses in
Education]: Computer-assisted instruction (CAI)

Introduction
Channels Service content
Channels services
Figure 1: A typical U-Cursos
view. Left: a list of current
channels (courses, communities
and associated institutions). Top
right: services available for the
selected channel. Bottom right:
contents of a service.
Figure 2: Cramped look to the
web interface from a smartphone.
Learning Management Systems (LMS), also known as
virtual learning environments, are systems used in the
context of educational institutions offering technology-
enhanced learning or computer-assisted instruction.
Stakeholders may have different objectives for using a
LMS. For example, Romero and Ventura’s review
comprising 304 studies [10] indicates that students use
LMS to personalise their learning, reviewing specific
material and engaging in relevant discussions as they
prepare for their exams. Lecturers and instructors use
them to give and receive prompt feedback about their
instruction, as well as to provide timely support to
students (e.g. struggling students need additional
attention to complete their courses more successfully [1],
as the failure to do so comes at a great cost, not only to
these students but to their institutions). Administrators
use LMS to inform their allocation of institutional
resources, and other decision- making processes [10].
These authors argue the need for the integration of
educational data mining tools into the e-learning
environment, which can be achieved via LMS.
LMS are being increasingly offered by Higher Education
institutions (HEIs), a technological trend making an
impact on these institutions. Another trend is the
proliferation of powerful mobile devices such as
smartphones and tablets, from which on-line resources can
be accessed. These two trends push HEIs to provide LMS
access via smartphones in a visually appealing and
accessible way. These are inherent requirements of the
mobile experience, which is fundamentally different to the
desktop (and even the laptop) one [2]. Benson and
Morgan [2] present their experiences migrating the
existing LMS StudySpace to a mobile development, as a
response to the pressures above presented and pitfalls
identified on the Blackboard Mobile app. Whilst this
in-house development seems to have met institutional
needs, students were not reported as having been involved
in the design. In fact, there seems to be little experience
in engaging students in LMS design. One example of such
kind of developments is the e-learning app Smart
Campus [3], however in this case the participation was
limited to 11 students. Another LMS, Dippler [5], also
differs from a traditional LMS because of the approach to
its design. However, Laanpere el al. employed
pedagogy-driven design in building Dippler [5], i.e. rather
than including students in the design process.
Against this context, lessons learned in mobile
development can be applied in education by exploiting
both the opportunity of the ubiquity of smartphones and
mobile Internet and the readiness to use them as exhibited
across the current generation of students1
. There have
been great efforts in this direction [4, 6], for example, in
studying transitions between formal and informal settings
that could be enabled by mobile technology in the context
of collaborative learning [12]; linking mobile learning with
offline experiences [11]; increasing students interaction [7];
and enabling ubiquitous learning in resource-limited
settings [9].
In this work we address the case of existent online services
which will be made accessible by mobile devices and how
the inclusion of users in the design process can inform the
development. We narrate our experience in making an
LMS mobile, starting with describing the U-Cursos system
and its current situation. Then we present a survey
applied to 4,000 users to include them in the design. In
doing so, we have identified the core requirements for a
1Mobile device purchases (and mobile Internet connections) per
capita in Chile are among the top five worldwide [8].

mobile application addressing issues with the current
platform. Finally, we describe ongoing follow-up work and
300,000
600,000
900,000
1,200,000
1,500,000
1,800,000
2,100,000
2,400,000
2,700,000
3,000,000
hits
month
1st
term
2nd
term
student
strike
Figure 3: Access graph between
2010 and 2014 for U-Cursos.
present our conclusions.
U-Cursos
U-Cursos is a web-based platform designed to support
classroom teaching. An in-house development by the
University of Chile, it was first released in 1999, when the
Faculty of Engineering required the automation of
academic and administrative tasks. In doing so, the
quality and efficiency of their processes improved, whilst
supporting specific tasks such as coordination, discussion,
document sharing and marks publication, amongst others.
Within a decade, U-Cursos became an indispensable
platform to support teaching across the University, used in
all 37 faculties and other related institutions.
The success of U-Cursos is demonstrated by the high
levels of use amongst students and academics, reaching
more than 30,000 are active users in 2013. U-Cursos
provides over twenty services to support teaching, as well
as community and institutional “channels”, which allow
students to network, share interests and engage in
discussion about various topics. Figure 1 shows a typical
view of U-Cursos. On the left, a list of “channels”
available for the current term are shown. Channels are the
“courses”, “communities” and “institutions” associated
with the user. Typically, courses are transient, so they are
replaced with new courses (if any) at the start of the
term. Communities are subscription channels which are
permanent and typically refer to special interest groups,
usually managed by students, with extracurricular topics.
Finally, institutions refer to administrative figures within
the organisation. The institutional channels are used to
communicate official messages on the news publication
service and also to allow students to interact using forums
containing students from all of the programmes within
each institution.
A number of services are available for each type of
channel. Users can select any of the shown services and
interact with it on the content area of the view. Note that
the majority of the services are provided for all types of
channels, but courses also offer academic services such as
homework publication and hand-in, partial marks
publication and electronic transcripts of the final marks.
These features make course channels official points of
access for the most important events in a course and have
become indispensable for students.
Current status
The current version of U-Cursos displays well on all
regular-size screens (above 9”), such as desktop
computers and tablets. However, the user interaction
becomes cumbersome on small displays, such as those in
smartphones, as shown in Figure 2.
Another shortcoming is the lack of notification facilities,
in particular those alerting users of relevant content
updates. The current setting requires users to manually
access the platform repeatedly to confirm that the
information is still current. This behaviour can be
observed in Figure 3, which shows access statistics of
U-cursos in the last four years. There are clear high-peaks
during the end-of-term periods2
.
Additional factors may trigger an increased access rate to
the service: students ask more questions and download
class material for the final exams, project coordination,
2Terms run from March to July and from August to December
in Chile. Some events may induce small variations on the actual
dates. The university closes for summer holidays in February. Source:
http://escuela.ing.uchile.cl/calendarios (In Spanish).

amongst others. According to the users, there is a
Figure 4: Services requested by
survey participants for a mobile
version of U-Cursos (shown in
decreasing order).
component of uncertainty which encourages users to
repeatedly access the platform during these periods. In
order to improve this and alleviate stress on students, we
designed a mobile application for the platform. Before
starting the design, we first surveyed the users in addition
to analysing the existing user statistics. This survey
allowed us to appreciate the actual user needs required for
a U-Cursos mobile client.
User survey for participatory design
As U-Cursos is a Learning Management System
completely implemented in-house, we have complete
flexibility to better address user-specific needs. Therefore
we decided to continue our work by including participatory
design. This is done by conducting a widely-applied survey
to gather information about the needs and expectations of
users towards a mobile version of the platform. We
published the survey in the U-Cursos platform, by doing
so we had guarantees that the survey is attempted by real
users only (and only once). The answers were stored
anonymously so they could not be used to identify users.
The survey contained four sections, namely: user profile,
current services, mobile services and other services. The
user profile section was included to understand the
context of users, and also to invite them to a follow-up
study concerning the impact of the mobile client. This
was stored separately from the rest of the survey. The
current services section allowed us to assess the perceived
need of implementing current services on a mobile version
of the system. Answers were on a 5-point Likert scale
ranging from “not interesting” to “very interesting”. The
mobile services section offered the users three services
which made sense only in a mobile device context: (1)
Find room (its building) using GPS, (2) Real-time
notifications and (3) upload files generated by a mobile
device (such as pictures). Answers were also on a 5-point
Likert scale. Finally, the other services section allowed
users to propose services they believed important for a
mobile version of U-Cursos via a free-text box.
Results
We presented the survey to U-Cursos’ users as a banner
at the top section of the main content area. They had the
possibility of answering the survey or permanently hiding
the banner. The survey was published during 2-9
September 2013. 4806 users took the survey, 580 of
whom left comments in the free-text box. The majority of
the responses came from students in their first years of
their programmes. The survey’s transcript, the
fully-anonymised dataset of responses and other
aggregated results are now publicly available3
.
Out of the surveyed users, 91% report owning a
smartphone (Android, iOS, Windows Phone or
Blackberry), while 6% own a basic mobile phone and less
than 1% do not own a mobile phone at all. These results
are consonant with expectations. As discussed earlier,
Chile’s per capita purchases of mobile devices and mobile
internet connections are among the top of the world.
Nevertheless U-Cursos’s accesses are predominately
performed from desktop computers with 87.3% of the
accesses made from Windows or OSX. Android appears
with 5.5% of accesses and iOS with 2.4%. Other mobile
platforms represent less than 1% of the total accesses.
Seemingly, U-Cursos access statistics are biased by the
type of platform, and despite the high ownership of mobile
devices (both nationwide and across our sample), they are
rarely used for accessing U-Cursos.
3Available from March 2014 at https://github.com/
niclabs/ucursos-survey-2013.

With regards to the appreciation of services, according to
Figure 4 users are more interested in key ones related to
current courses activities: partial marks, news, upload
files, homework assignments and course forums. Other
aspects, less related to the courses, are not as well
supported. For the proposed mobile-only services, the
Current services
My timetable (92)
E-mail (74)
Notifications (70)
Teaching material (58)
Calendar (50)
Partial marks (46)
Forum (20)
Dropbox (14)
Guidance marks (11)
Homework (7)
News (7)
Access to past courses (5)
Favourites (3)
New mobile features
Granular push (20)
Preview material (11)
Classroom finder (10)
More simplicity (9)
Attendance log (5)
People search (4)
Offline access (4)
Book a lab (4)
Timeline (4)
Certificate requests (4)
Android widget (4)
Marks calculator (4)
Google drive (3)
Table 1: U-Cursos services
ranked in ascending order of
popularity amongst users
according to comments in an
optional free-text box in the
survey. The number in
parenthesis is the number of
users mentioning the feature.
Only those requested by 3 users
or more are reported here.
majority of the answers were positive (over 70% of
positive feedback for all of them). The survey responses
(particularly in the free-text box provided) show users’
acute awareness of the need for mobile access and
real-time notifications within the U-Cursos service.
A mobile app for U-Cursos
From the results of the survey and the statistical
information from U-Cursos, we have defined the basic
requirements for a mobile version. These are: real-time
notifications using push notifications facilities from the
different vendors, prompt access to current courses
services and appropriate views for each service, specially
for those which impact academic performance. From users
we learnt we must provide a channel selection function to
allow then select which notifications they want to receive.
In regards of the implementation, a 100% HTML5
responsive site was considered but we also need to
implement real-time notifications (platform-specific). We
then decided to develop native versions of the U-Cursos’
mobile client for the two major vendors. The target
platforms are Google Android and Apple iOS since they
currently cover over 80% of the mobile market.
As mentioned, we offered a free-text box at the end of the
survey. We received comments from 580 users giving us
the possibility to explore aspects that people wanted to
communicate about the system. We identified the
concepts mentioned in each comment and summarised
them in Table 1, showing that users are mostly interested
in course-related tasks (partial marks and homework).
They also identify the need of real-time notifications to
become aware of important information updates.
Regarding novel features for a mobile application, users
were concerned about receiving too many real-time
notifications, specifically from institutional forums which
collectively can generate over a thousand new messages a
day. Users also suggested additional features to take
advantage of the mobile device.
Future work
The participatory design here presented is currently being
evaluated through a alpha release of the first mobile client
implementation for U-Cursos. We are currently studying
the effects of improved accessibility to course contents
and real-time notifications to reduce information
uncertainty which in turn reduces stress amongst users.
Randomly selected volunteers amongst participants of the
survey here presented have agreed to disclose their
U-Cursos’s activity (effectively being tracked) on
March-July 2014. As part of the study, they will
participate on a survey again at the end, to evaluate their
experience with the new application.
Further research will involve the analysis of academic
information stored in the U-Cursos servers to support
students and further improve services.
Conclusions
Web-based platforms offering critical services to their
users may produce stress due to information uncertainty
under limited access conditions and when real-time
updates are not available. We have presented the case of
U-Cursos a widely used web-based platform to support
classroom teaching in the University of Chile. We have

also presented how participatory design was used in the
design of the mobile version of the platform. Through this
process the need for enhanced display in small screens
(such as in smartphones) and real-time notifications were
identified, to curb the need to log into a desktop
computer repeatedly for access to up-to-date information.
A survey of more than 4,000 users led to uncover the need
to reduce information uncertainty on student-critical
services such as classroom changes and marks publication.
This work also shows how users can become involved in
the design by defining accurately the relevant features to
improve a long running service. Finally, we show that
users participation can be done in large numbers with
moderate effort as achieved through U-Cursos.
Acknowledgements
This work was partially funded by CIRIC-Inria Chile and
NIC Chile.
References
[1] Baepler, P., and Murdoch, C. J. Academic Analytics
and Data Mining in Higher Education. International
Journal for the Scholarship of Teaching and Learning
4, 2 (July 2010).
[2] Benson, V., and Morgan, S. Student experience and
ubiquitous learning in higher education: impact of
wireless and cloud applications. Creative Education 4
(2013), 1.
[3] Di Fiore, A., Chinkou, J. L. F., Fiore, F., and
D’Andrea, V. The need of e-learning: Outcomes of a
participatory process. In e-Learning and
e-Technologies in Education (ICEEE), 2013 Second
International Conference on, IEEE (2013), 318–322.
[4] Hwang, G.-J., and Tsai, C.-C. Research Trends in
Mobile and Ubiquitous Learning: A Review of
Publications in Selected Journals from 2001 to 2010.
British Journal of Educational Technology 42, 4
(2011), E65–E70.
[5] Laanpere, M., Põldoja, H., and Normak, P.
Designing dipplera next-generation tel system. In
Open and Social Technologies for Networked
Learning. Springer, 2013, 91–100.
[6] Laine, T. H., and Joy, M. S. Survey on
Context-Aware Pervasive Learning Environments.
International Journal of Interactive Mobile
Technologies (iJIM) 3, 1 (2009), 70–76 and
references therein.
[7] Laine, T. H., Vinni, M., Sedano, C. I., and Joy, M.
On Designing a Pervasive Mobile Learning Platform.
ALT-J, Research in Learning Technology 18, 1
(March 2010), 3–17.
[8] Ministerio de Transportes y Telecomunicaciones, G.
d. C. Radiografı́a de Servicios de Internet Fija y
Móvil, 2012.
[9] Pimmer, C., Linxen, S., Gröhbiel, U., Jha, A. K., and
Burg, G. Mobile learning in resource-constrained
environments: A case study of medical education.
Medical teacher 35, 5 (2013), e1157–e1165.
[10] Romero, C., and Ventura, S. Educational data
mining: a review of the state of the art. Systems,
Man, and Cybernetics, Part C: Applications and
Reviews, IEEE Transactions on 40, 6 (2010),
601–618.
[11] Saatz, I. Linking mobile learning and offline
interaction: a case study. In Proceedings of the 2013
ACM conference on Pervasive and ubiquitous
computing adjunct publication, ACM (2013),
1389–1392.
[12] Scanlon, E. Mobile learning: location, collaboration
and scaffolding inquiry. Increasing Access (2014), 85.

Appendix F
U-Campus Screenshots
Figure F.1: U-Campus courses catalogue. To the left, all faculties currently using
U-Campus. In the main frame, each course offered by the selected faculty (in this case,
Mathematical and Physical Sciences) are displayed.
75

Appendix F U-Campus Screenshots 76
Figure F.2: U-Campus module catalogue for the Computer Science course. The
main panel now shows module information, indicating full name, number of credits,
pre-requisites, equivalences to modules no longer offered, as well as current information
(for the selected semester, in this case, Autumn 2014) such as lecturer details (clickable),
number of places remaining for the module, and timetabling information. In many cases,
the syllabus of the module is also available.

Appendix G
Chilean University Selection Test
The University of Chile admits approximately 4,600 students every year, selected via a
University Selection Test (PSU, Prueba de Selección Universitaria). The following are
screenshots of the portal (in Spanish) for prospective applicants.
Figure G.1: Prueba de Selección Universitaria (PSU) sample screenshot for step 1
of the application process. Available at http://www.demre.cl/instr_incrip_p2014_
paso1.htm (last accessed 3th
July 2014)
77

Appendix G Chilean University Selection Test 78
July 2014)

July 2014)

Appendix H
Additional research
As part of my research I have also investigated other aspects only marginally related
to the study of behaviour in Higher Education students. In particular, in Section H.1
I studied audience response systems and their effectiveness as hand-held devices in the
classroom, both from a theoretical point of view, and anecdotal one (experiencing first-
hand their effectiveness, yet without the necessary rigour for it to be regarded a scientific
experiment). In H.2, I have explored the disconnect between privacy intentions (as de-
clared by smartphone users) and the level of privacy actually found in their phone inter-
actions. Other aspects include the practical feasibility of the development of inexpensive
devices of the Internet of Things (IoT) considered in Section H.3, which will force us to
revisit concepts of Activity Theory under IoT as our interaction with others becomes
mediated through objects capable of interacting with us and other objects (Section H.4).
H.1 Audience response systems (zappers)
A great variety of systems based on handheld devices are already being used in the
classroom. One example are electronic voting systems (also known as audience response
systems), comprising of a USB receiver and a set of handheld devices commonly known
as zappers (in the UK) and clickers (in the US). These are transmitters of a similar size to
a small calculator (Figure H.1), which can be used by students to answer multiple-choice
questions set up on a screen (Caldwell, 2007).
Evidence suggests that zappers can be used to increase student participation in
lectures, and to foster discussion and attentiveness, especially in large classes, where
these are challenging issues. In addition to being used for questions about the learning
matter, zappers have also been found to be useful as a means to discuss classroom policy
and allow for formative feeedback on the teaching methods and pace of the lectures
(Gunn, 2014). However, a problem associated with the adoption of zappers (besides
81

Appendix H Additional research 82
Figure H.1: A commercial zapper: A TurningPointTM
response card
(http://www.turningtechnologies.co.uk).
their expense) is that they require significant setting-up time and administration, as
well as thoughtful design of effective questions. Moreover, zappers have been reported
to add little value in time-constrained lectures where a great amount of content needs
to be covered (Kenwright, 2009).
Personal digital assistants (PDAs) and smartphones1 can also be used as zappers in
order to engage students. For example, Estrems et al. (2009) encouraged their use in
the lecture as zappers2, challenging the common preconception that these devices are
disruptive for learning. As a result, engagement levels have reportedly risen in their
experience, as these devices were used to interact with each other, with the lecturers,
and with the learning material, rather than with the distractions of the “outside world”.
This finding is echoed by Anderson and Serra (2011), who report used Wi-Fi enabled
devices (such as smartphones, iPads, and iPod touch devices) in the classroom to access
the Blackboard VLE and the survey platform SurveyMonkeyTMto increase participation.
H.1.1 Own experience with zappers
To experience first-hand the surveyed benefits and problems of using handheld devices
in the classroom, I trialled zappers in some lectures. Specifically, I used these devices
with students enrolled in the following ECS modules during 2012/13:
• Wireless and Mobile Networks (ELEC6113), in the MSc in Wireless Communica-
tions (class size: 81 students);
1
Smartphones is the preferred term above others. See discussion at http://www.allaboutsymbian.
com/features/item/Defining_the_Smartphone.php (Accessed: 24th
February 2014).
2
A commercially available example of how to use smartphones as zappers is with the PollEv Presenter
App (http://www.polleverywhere.com/app, last accessed 24th
February 2014).

Figure H.2: Example exam question with student responses
• Computer Networks (ELEC3030), in the BEng/MEng in Electrical and Electronic
Engineering (36 students); and,
• Data Communication Networks (INFO2006), in the BSc in Information Technology
in Organisations (34 students).
As planned, each class used zappers in two lectures during the semester. It is worth
stressing that, rather than being set up as a formal experiment, the intention behind
the trial the use of zappers in these lectures was to experience first hand the benefits
and problems described in the literature.
Sets were primarily facilitated by the Hartley Library3, and twice by Adam Warren
from the Centre for Innovation and Technologies in Education (CITE). I followed the
tutorials produced by CITE for using zappers in lectures, and spent additional effort in
selecting relevant questions that could use well the technology. The estimated setting-
up effort (including the training) was approximately ten hours. As an example of how
zappers were used in these lectures, Figure H.2 shows a past-papers question4, with five
possible answers. In this example, four wrong answers were offered, each illustrating
a typical mistake of students who have not yet mastered the material (e.g. errors in
units, misunderstanding of what each of the elements in the formula represent, and
manipulating the given information). After five minutes of work, during which students
could consult their notes, students were encouraged to discuss in pairs their workings
for a further 3 minutes. At this point, they were asked to select an answer. Once the
poll was closed, the class responses were displayed on the slide.
Since it was of interest not only whether they were able to arrive to the correct
result, but also their confidence on their mastery of the material, a further question was
3
Following procedures outlined in http://www.soton.ac.uk/library/services/zapperloans.html,
last accessed: 29th
January 2013)
4
Question B2(a) from exam paper ELEC6113W1 in the academic year 2011/12. Worth 7 marks out
of a total possible of 75 marks.

asked, to gauge the understanding of the topic as a collective and, as the most ‘popular’
chosen answer turned out to be incorrect, instant feedback was facilitated in a way that
could have been difficult otherwise. Immediately after working out the correct answer on
the board and highlighting the problems that could have resulted in each of the wrong
answers, students were encouraged to re-appraise their self-assessment of their answers
and, in doing so, received reassurance that as a collective they were doing rather well,
though they still need to be careful about certain aspects (Figure H.3).
Figure H.3: Zappers in action: Appraising students confidence on their self-
assessment
before (left slide) and after (right slide) the solution was discussed in class.
Whilst this exercise was especially helpful in the large class scenario (ELEC6113),
it was not worthwhile in the smaller classes (ELEC3030 and INFO2006). In the latter,
students are able to interact directly with each other and with the lecturer without the
barriers presented in a large class (of mainly international students). In these cases,
informal feedback can be provided in an efficient way without the need for this resource,
so the perceived benefits of the use of zappers did not compensate the overheads re-
lated to the administration of the devices and the additional preparation, confirming
the criticisms outlined by Kenwright (2009). Other hand-held devices5, which may re-
quire Internet connectivity, may be affected by other issues when used in the classroom.
With large classes becoming a trend, this early experience using zappers proved to be a
positive one, however, other factors influencing its success need to be explored (such as
the ’novelty’ factor) before drawing firm conclusions. I have shared these preliminary
reflections with the teaching community (Wilde, 2014).
H.2 Privacy
Revisit
for flow
Revisit
for flow
5
For example, the PollEv Presenter App or similar.

Many of the studies in the literature review deal with privacy concerns by assuring
participants that the data would be anonymised and used securely for research purposes
only. Longer term, Eagle and Pentland (2006) assert that as future phones grow in
computational power, they would become able to make most of the inferences locally,
without requiring any sensitive information even to leave the handset of concerned users.
In the context of higher education, there is a commonplace observation regarding
the use of sensitive or private data: only a minimal percentage of students using social
networks customise their privacy settings. From research with 4,000 university students,
Gross and Acquisti (2005) observed that “while personal data is generously provided,
limiting privacy preferences are hardly used”, making it easy for outsiders to create a
model of behaviour based on Facebook data. This is consistent with the findings by
Griswold et al. (2004). Within their ActiveCampus project, students disclosed their
location information widely, and only 1% changed their default settings to hide location
from their peers.
The above does not imply that students would necessarily agree to the use of such
data for the purpose intended here, in fact, as Fraser, Rodden, and O’Malley (2007)
found, even within circles with high levels of trust, such as between family members,
trust “did not always lead to acceptance of ubiquitous information capture and dis-
closure” with the purpose of developing a pervasive education system. Furthermore,
Hughes (2007) argues that e-learning communities, despite their potential for inclusive-
ness, present certain challenges, as diversity and belonging to online learning groups is
not easily understood. Individuals may be at ease reconciling multiple identities in chat
rooms and games, but it is not so easy to reconcile social identities, such as class and
gender, with being a student. Students might become reluctant to take part of studies
which would require of them the disclosure of sensitive data, and result in being labelled
“good students” or otherwise. I investigated these concerns through a survey of HE stu-
dents (see Section ?? and Appendix C). These concerns, amongst others, had also been
identified by Srivastava et al. (2012). Specifically, they identify the following challenges
in using smartphones for human sensing:
• identifying the appropriate set of individuals for whom data could be collected
(self-selected or not);
• identifying a subset of individuals who satisfy requirements such as having the
right phones and being in the area during the data collection period;
• addressing problems such as self-selection bias related to the application of an open
call, perhaps by shaping the set of actual contributors to prevent statistical bias
in the data collection;
• fitting to cost and resource constraints;

• applying methods to keep the participants engaged and hence minimise costly
withdrawals from the study;
• rate contributions to assign reputation to participants (which can be used to alter
the participants set during a campaign or to inform future campaigns).
Srivastava et al. (2012) acknowledge that data-collection campaigns are powerful
thanks to the human element but these challenges arise precisely because of being hu-
man: “potential participants may have different motivations, availability, diligence, skill,
timeliness, phone capabilities and privacy constraints that would affect the amount and
quality of data they collect” .
Existing studies have suggested a disconnect between users’ stated view of privacy
and their acted behaviours (Balebako et al., 2011). For example, often, their actions
do not reflect their intentions of preserving privacy. This problem may have arisen as
“privacy”, as many words in common use, is hard to define universally and unequivocally.
The meaning may change from person to person, and it is intimately related to identity
and trust. In addition, whichever working definition of privacy may be chosen, users
may not be willing or able to perform the appropriate actions to preserve it, resulting in
behaviour that may not be consonant with their core values. Lack of awareness prevents
a thorough evaluation of this situation, and users may simply expect others to respect
(or even protect) their privacy.
Having observed this apparent “disconnect” whilst analysing the data from the sur-
vey I conducted with HE students (see Appendix C), I produced a proposal for a research
project to investigate further this area, with colleagues Andrew Paverd, Oliver Gasser
and Moira McGregor, all members of the Network of Excellence in Internet Science
(EINS), from the Universities of Southampton, Oxford, Munich and Stockholm respec-
tively. The proposed project was titled “EINS PRIME - Perception and Realisation
of Information privacy using Measurements and Ethnography” (Wilde et al., 2013b).
In greater detail, this project would seek to investigate how information privacy is per-
ceived and enforced by users. Specifically, this project intends to measure the disconnect
between perceptions of information privacy and the actions towards its preservation,
studying it quantitatively and qualitatively, in order to identify areas of improvement
and inform policy.
A short summary was presented at the Digital Economies Workshop “Towards Mean-
ingful: Perspectives on online consent”, part of the DE2013: Open Digital Conference
held in Manchester on the 5th November 2013 (Wilde et al., 2013b).

H.3 Internet of Things
One of the studies reviewed in Chapter 2 used smart devices in the classroom to give
instant feedback to lecturers on lecture quality, creating effectively a “smart classroom”
which detected levels of attention of participants, and being able even to detect whether
the students were “fidgeting” (Gligoric, Uzelac, and Krco, 2012).
The practical feasibility of a wider implementation of this proof-of-concept study
across the many learning environments in higher education institutions depend mainly
on the development of low-cost general-purpose devices for the Internet of Things. I
pursued this topic by supervising an Electronic Engineering student, Richard Oliver,
who developed a low-cost general-purpose IoT device which I presented in the 7th Inter-
national Conference on Sensing Technology, in Wellington, New Zealand (Wilde, Oliver,
and Zaluska, 2013a).
H.4 Activity Theory
The emergence of the Internet of Things forces us to rethink the way humans interacted
with objects whilst pursuing their activities. This theme is the subject of a paper pre-
sented at the 1st International Workshop on Internet Science and Web Science Synergies,
which was collocated with the ACM Web Science Conference. The title of the paper is
“Revisiting activity theory within the Internet of Things” (Wilde and Zaluska, 2013).

A Mini-Thesis Submitted For Transfer From MPhil To PhD Predicting Student Success With Learning Analytics On Big Data Sets Conditioning And Behavioural Factors

More Related Content

Similar to A Mini-Thesis Submitted For Transfer From MPhil To PhD Predicting Student Success With Learning Analytics On Big Data Sets Conditioning And Behavioural Factors (20)

More from Joaquin Hamad (20)

Recently uploaded (20)

A Mini-Thesis Submitted For Transfer From MPhil To PhD Predicting Student Success With Learning Analytics On Big Data Sets Conditioning And Behavioural Factors