Technology Enabled Learning to Improve Student Performance: A Survey

Integrated Intelligent Research (IIR) International Journal of Data Mining Techniques and Applications
Volume 5, Issue 1, June 2016, Page No.50-56
ISSN: 2278-2419
50
Technology Enabled Learning to Improve Student
Performance: A Survey
M.Pazhanivel1
, T.Velmurugan2
1
Research Scholar, Bharathiar University, Coimbatore, India.
2
Associate Professor, PG and Research Dept. of Computer Science and Applications, D. G. Vaishnav College, India.
E-Mail: mrpvel@gmail.com, velmurugan_dgvc@yahoo.co.in
Abstract–The use of recent technology creates more impact in
the teaching and learning process nowadays. Improvement of
students’ knowledge by using the various technologies like
smart class room environment, internet, mobile phones,
television programs, use of iPods and etc. are play a very
important role. Most of the education institutions used
classroom teaching using advanced technologies such as smart
class environment, visualization by power point projector and
etc. This research work focusses on such technologies used for
the improvement of student’s performance using some of the
Data Mining (DM) techniques particularly classification and
clustering. Information repositories (Educational Data Bases,
Data Warehouses) are the source place for collecting study
materials and use them for their learning purposes is the
number one source for preparation of examinations.
Particularly, this research work analyzes about the use of
clustering and classification algorithms to enable the student’s
performances and their learning capabilities using these
modern technologies. During the study period, the student’s
family background and their economic status are also play a
very important role in their daily activities. These things are
not considered in this survey work. A comparative study is
carried out in this work by comparing students performance
based on their results. The comparison is carried out based on
the results of some of the classification and clustering
algorithms. Finally, it states that the best algorithm for the
improvement of students performance using these algorithms.
Keywords: Technology Enabled Learning, Student
Performance, Clustering Algorithm, Classification Algorithm
I. INTRODUCTION
The significance of technologies cannot be overemphasized in
education. Computers have been generally accepted as modern
instruments that enable the teachers/lecturers to select the
teaching methods that will increase students’ (learners’)
interest in learning. Computer is an electromechanical device
designed to sequentially accept, process and store data on the
basis of set of instructions to produce useful information. The
students’ academic performance can be referred to as the
competencies, skills acquired and attitudes learned through the
education experience. The main objective of this paper is to
discuss the use of classification and clustering algorithms in
data mining for the improvement of students performance by
using some or most of the recent technologies in the modern
world. Only a comparative analysis is performed in this
research work using the stated DM algorithms. During this
study, it is not considered all types of classification and
clustering algorithms, which is limited to certain algorithms
alone.
DM is more familiar tool for extract the information from large
number of different kinds of data repositories. Data mining
takes major role in the part of learning data mining (LDM). It
tries to discover a system to acquire new knowledgefrom the
existing information about learners to understand the
development of learning and the social and inspiration of the
factors envelop learning. In learning field, data mining
methods are very useful for enhancing the current learning
standards and managements. The size of data is gathers from
different meadow exponentially increasing. Data mining has
been used special scheme at the intersection of Machine
Learning, Artificial Intelligence and statistics. The data mining
process is to extract information from huge datasets and
transform it into understandable structure for further use. Data
mining techniques which extract information from huge
amount of data have been becoming popular in education
domains. These methods provide a direction to a multiple level
of grade, a finding which gives a new sensitivity of how people
can becomeskillful in these learning sectors. Data mining has
different methods such as Prediction, Association rules,
Decisions Tree,Classification, Clustering, Neural Networks
and many others. In the middle of these, classification
algorithm such as Decision tree ID3 and C4.5 algorithms plays
an essential role in LDM. Decision tree induction algorithms
can be used for classification in many application areas, such
as Education, Medicine, Manufacturing, Production, Financial
analysis, Fraud Detection and Astronomy etc. There are several
data mining algorithms such as k-Means, C4.5, SVM, Apriori,
Naive Bayes, EM, PageRank, AdaBoost, kNN, and CART etc,
which are effectively utilized for classifying the students
learning category. A number of clustering algorithms are also
applied in LDM for the grouping of student’s categories in
order to partition the students based on their learning
maturities.
With some of these possible methods, one can search an
important secreteblueprint for pronouncementopportunity
direction and rally round in decision making. Data mining rally
round learners by managing effective learning units,
redesigning the prospectus and humanizing learning methods.
There are number of algorithms in Data Mining, in which
decision tree algorithms are the majorly used because of its
easy implementation. Identity-efficacy has been related to
resolution, resolve, and achievement in learning settings. A
meta-investigation of study in learning settings found that
identityvaluewas related both to academic performance and
persistence. The contribution of self-efficacy to learning
achievement is based both on the increased use of particular
cognitive activities and strategies and on the positive contact of
efficacy beliefs on the broader, more general classes of meta
cognitive skills and coping abilities.

ISSN: 2278-2419
51
Computer based experiment have been used since 1960s
to experiment information and problem solving skills.
Computer based evaluation systems have enabled learners
and trainers to author, scheduler, deliver and report on
investigation, quizzes, experiment and exams.An effective
method of student assessment technique is necessary in
assessing student knowledge. Due to an increase in student
numbers, ever-escalating work commitments for academic
staff, and the advancement of internet technology, the use of
computer assisted evaluation has been an attractive
proposition for severalsenior learning institutions.This paper
has an insight of students learning perspectives via the recent
technologies used for their knowledge growth and improving
result performance in the examination of their course
examinations.
The structure of this research paper is organized as follows.
Section II discusses about the research work carried out by
using technology oriented students’performance
improvements. The role of classification algorithms for LDM
is illustrated in section III, which also have a discussion about
the use theclassification algorithms Naïve Bayes, J48 and
Support Vector Machines. The use of clustering algorithms for
LDM is illustrated in section IV. Finally, section V concludes
with the research work.
II. TECHNOLOGY ORIENTED STUDENTS
PERFORMANCE IMPROVEMENTS
In recent days, the impact of new technologies have a powerful
influence on all aspects of our society, from various domains
of real would situations.Evidently, education is not an
exception. Many technologies have an impact on the way we
teach and learn. For example, new mobiledevices (e.g.,
smartphones and tablets) raise student engagement in both
indoor and outdoor activities with applications such as
mobileaugmented reality. Also, some of the social networks
play a very vital role in current scenarios. New motion sensors
and image-recognition technologies are giving rise to
applications with more natural interactionmethods, helping
non-technical users to interact with computer-based systems, as
in the case of new-generation video consoles. In addition,social
networks and web tools give students a more active role in
their own education, allowing them to become educational
presumes.
Many peoples are carrying out research based on the
improvement of student’s performance using the recent
technologies. This section discusses about such articles with an
overview of how they chosen data set, what kind of data are
selected so for, and what technology utilized for their
knowledge improvements. A research paper titled as"Using
learning analytics to predict (and improve) student success: A
faculty perspective" was done by Dietz-Uhler et al. [1]. In this
paper, they define learning analytics, how it has been used in
educationalinstitutions, what learning analytics tools are
available, and how faculty can make use of data intheir courses
to monitor and predict student performance. Finally, they
discuss several issues andconcerns with the use of learning
analytics in higher education.This studies have indicated
individual faculty can make use of the data they have available
in their courses to affect changeand improve student success.
These efforts, although seemingly “small-scale”, can have a
largeimpact on student success.
Another paper titled as “New technology trends in education
seven years of forecasts and convergence” is discussed by
Martin et al. [2]. They analyzed the evolution of technology
trends from 2004 to 2014 that relate to the long-term
predictions of the most recent distancereport. The study
analyzed through bibliometric analysis which technologies
were successful and became a regular part of education
systems, which ones failed to have the predicted impact and
why, and the shape of technology flows in recent years. The
study also displays how the evolution and adulthood of some
technologies allowed the renewal of expectations for others.
They conclude that the analysis gives some of the methods
used is right and some are not in suitably handled.
Another research work titled as"Data mining application in
higher learning institutions" was done by Delavari et al.[3].
They studied capabilities of data mining in the background of
higher educational system by i) proposing an analytical
guideline for higher education institutions to improve their
current decision processes, and ii) applying data mining
techniques to find out new explicit knowledge which could be
helpful for the decision making processes.Their final results
had been analyzed and validated with real situations in a
university. The factors affecting the anomalies had been
discussed in detail. The final result from each model with
various techniques, presented that they are all performing
similarly.
Peng et al. [4] propose a survey on "A descriptive framework
for the field of data mining and knowledge discovery". This
paper analyses a vast set of data mining and knowledge
discovery(DMKD) literature to give a comprehensive image of
current DMKD research and categorize these research works
into high-level categories using grounded theory method, it
also appraises the longitudinal variations of DMKD study
behavior during the last decade. This paper agreed eight main
areas of DMKD: DM tasks, learning techniques and methods,
mining complex data, fundamentals of DM, DM software and
schemes, high performance and distributed DM, DM
applications, and DM method and project.
A paper titled "A mobile learning system for scaffolding bird
watching learning" carried out by Chen et al. [5]. They aimed
to build an outdoor mobile-learning activity by means of up-
to-date wireless technology. They future Bird-Watching
Learning (BWL) system is aimed using a wireless mobile ad-
hoc network. In the BWL method, each learner has a Personal
Digital Assistant (PDA) with a Wi-Fi-based wireless network
card. The BWL system provides a mobile learning structure
which supports the students learning through scaffolding. The
goal of a formative assessment was twofold: to shows the
expected roles and scaffolding helps that the mobile learning
method offers for bird-watching activities and to examine
whether student learning profited from the mobility,
movability, and individualization of the mobile learning
device. They concluded that The BWL system was specifically
developed to integrate the scaffolding model with the system.
Three elementary schools in Taiwan used the BWL system for
bird-watching. A formative evaluation from their experiences

ISSN: 2278-2419
52
was undertaken. Based on these findings, it was found that the
children who used the bird watching system improved their
learning, above and beyond what would normally be expected
they would learn.
Likewisea paper "A review of recent advances in learner and
skill modeling in intelligent learning environments" was
explored by Desmarais et al. [6]. They review the learner
models that have played the largest roles in the success of these
learning environments, and also the latest advances in the
modeling and assessment of learner skills. They concluded by
discussing related advancements in modeling other key
constructs such as learner motivation, emotional and attention
state, meta-cognition and selfregulated learning, group
learning, and the recent movement towards open and shared
learner models.
Aleksandraet al. [7] proposed a paper titled as "e-learning
personalization based on hybrid recommendation strategy and
learning style identification". This structure identifies different
patterns of learning stylishness and learners’ habits through
testing the learning styles for students and quarrying their
serverlogs. Firstly, it processes the clusters based on different
learning methods. It examines the habits and the interests of
the learners through mining the numerous sequences by the
Apriori algorithm. Finally,this system finishes personalized
recommendation of the learning content rendering to the scores
of these numerous sequences, provided by the Pouts system.
Some experiments were carried out with tworeal groups of
learners: the experimental and the control group. Learners of
the control group learned ina normal way and did not receive
any recommendation or guidance through the course, while
thestudents of the experimental group were required to use the
Protus system. The results show suitabilityof using this
recommendation model, in order to suggest online learning
activities to learners based ontheir learning style, knowledge
and preferences.This paper describes a personalized e-learning
system which can automatically adapt to the interests, habits
and knowledge levels oflearners. The differencesbetween the
learners are determined according to their previous knowledge
of the matter, their learning style,their learning characteristics,
preferences and goals.
DM scheme have to do with the discovery of secreted
association to facilitateindividual in learning databases. As we
identifyextensiveassortment of information is stored in learning
databases, so in order to get required data and to find the
secreted relationship, for that different data mining scheme are
developed and used. Some of the articles discussed here
provide a better understanding in learning resources.
III. ROLE OF CLASSIFICATION ALGORITHMS FOR
LDM
Learning data mining is explain part of scientific doubt come
to mind mainly and around the progress of methods for making
breakthrough within the singular kinds of data that come from
learning settings, and using those methods to better understand
students and the settings which they learn. This section
discusses about the difference between consequences of
students performance learning evaluation system that they use
the classification algorithms. Many investigators explores
about Students Performance Learning System (SPLS) in their
research work.Classification is aneasymethod of noticea
prototype that recognizes the relevant features of information
classes or impression, for the purpose of being able to use the
model to guess the class of stuff whose class marker is
nameless. It calculateseparate and unordered marker in huge
information sets.Institutions across the sphere are migrating
toward the use of Technology Based Learning (TBL) to
improve students’ knowledge. The advantages of using
computer knowledge for learning measurement in a global
sense have been recognized and these include lower
administrative cost, time saving and less demand upon
teachers among others.
Saeed et al. [8] proposed a case study on "Emerging Web
technologies in higher education: A Case of incorporating
blogs, podcasts and social bookmarks in a web programming
course based on Students' Learning Styles and technology
preferences". This research work has been suggested to
incorporate evolving web technologies into higher education
based on student’s learning methods and technology
preferences and a case study has been approved to authorize
the proposed structure. An achievement research methodology
has been assumed to carry out the study, which covers a study
about student’s learning methods and technology preferences
and incorporating a combination of developing web
technologies based on the review findings; and examining key
achievements and deficiencies of the study to redefine research
purposes. The study delivers support for the suggested
framework by highlighting the significant relationships among
student’s learning methods and technology preferences and
their impact on academic presentation. Their findings propose
that today’s learners are flexible in stretching their learning
methods and are able to accommodate different instructional
policies including the use of evolving web technologies. They
further proposed that learning methods of today’s learners are
flexible enough to understanding different technologies and
their technology preferences are not restricted to a particular
technology.
Another article titled as "Microblogs in Higher Education–A
chance to facilitate informal and process-oriented learning?"
was done by Ebner et al. [9]. This paper reports on a research
study that was carried outon the use of a microblogging
platform for process-oriented learning in Higher Education.
Students ofthe University of Applied Sciencesin Upper Austria
used the tool throughout their course. All postingswere
carefully tracked, examined and analyzed in order to explore
the possibilities offered by microbloggingin education. It can
be concluded that microblogging should be seen as a
completely new form ofcommunication that can support
informal learning beyond classrooms.
Yadav et al.[10] proposed prediction in a paper titled "Data
mining: A prediction for performance improvement of
engineering students using classification". In this paper,
Classification methods like decision trees, Bayesian network
etc can be applied on the learner data for calculating the
student’s performance in examination. This prediction will
help to find the weak students and help them to score better
marks. The C4.5, ID3 and CART decision tree algorithms are
applied on engineering student’s data to predict their
performance in the last semester examinations. The result of

ISSN: 2278-2419
53
the decision tree expected the number of students who are
likely to pass, fail or promoted to succeeding year. The results
offer steps to increase the performance of the students who
were expected to fail or promoted. After the announcement of
the results in the final examination the marks acquired by the
students are fed into the system and the results were examined
for the next session. The comparative study of the results states
that the prediction has helped the weaker students to improve
and got out improvement in the result.They suggested that the
Machine learning algorithms such as the C4.5 decision tree
algorithm can learn effective predictive models from the
student data accumulated from the previous years. The
empirical results show that we can produce short but accurate
prediction list for the student by applying the predictive models
to the records of incoming new students. This study will also
work to identify those students which needed special.
Wu et al. [11] have conducted a survey on “Top 10 algorithms
in data mining”. This paper offerings the top 10 data mining
algorithms approved by the IEEE International Conference on
Data Mining (ICDM) in Dec. 2006. C4.5, k-Means, SVM,
Apriori, EM, PageRank, AdaBoost, kNN, Naive Bayes, and
CART are considered for this analysis. These top 10
algorithmsare among the most influential data mining
algorithms in the research community in all fields of DM and
its applications. They analyzed with a formal tie with the
ICDM conference, Knowledge and Information
Systemshasbeen publishing the best papers from ICDM every
year, and several of this papers citedfor classification,
clustering, statistical learning, and association analysis were
selected bythe previous year ICDM program committees for
journal publication in Knowledge and Information
Systemsafter their revisions and expansions. In the same
conference many of the articles discussed about the use DM
algorithms for the prediction of student’s performance by using
the various DM algorithms.
A paper titled as "Constructing a personalized e-learning
system based on genetic algorithm and case-based reasoning
approach" was done by Huang et al. [12]. Their suggested
approach is built on the evolvement method through
computerized adaptive testing (CAT). Then thegenetic
algorithm (GA) and case-based reasoning (CBR) are engaged
to build an optimal learning path for each pupil. This paper
makes three critical contributions: (1) it presents a genetic-
based curriculum sequencing approach that will generate a
personalized curriculumsequencing; (2) it illustrates the case-
based reasoning to develop a summative examination or
assessment analysis; and (3) it usesempirical research to
indicate that the proposed approach can generate the
appropriate course materials for learners, based on
individuallearner requirements, to help them to learn more
effectively in a Web-based environment.
Kotsiantis et al. [13] predicting students performance in the
article "A combinational incremental ensemble of classifiers as
a technique for predicting students’ performance in distance
education". This paper predicts a student’s performance could
be useful in a great number of different ways associatedwith
university-level distance learning. Students’ marks in a few
written assignments can constitutethe training set for a
supervised machine learning algorithm. Along with the
explosive increase ofdata and information, incremental
learning ability has become more and more important for
machinelearning approaches. The online algorithms try to
forget irrelevant information instead of synthesizingall
available information. Nowadays, combining classifiersis
proposed as a new direction for the improvement of the
classification accuracy. Among other significant conclusions it
was found that the proposed algorithm isthe most appropriate
to be used for the construction of a software support tool.
Recent Methodologies for Improving and Evaluating
Academic Performance is carried out by Ajay Varmaand Y. S.
Chouhan in [14]. The aim of this study is to provide the review
of different data mining techniques that have been used in
educational field with regard to evaluation of students’
academic performance. Academic Data Mining used many
techniques including classification algorithms and many
others. Using these techniques many kinds of knowledge can
be discovered such as association rules, classifications and
clustering. The discovered knowledge can be used for
prediction and analysis purposes of student patterns.The
literature indicates that among the three methods of
classification with respect to academic performance, the most
widely used classification techniques in educational domain is
decision tree.
Zafra et al. [15] analyzed a paper titled "Multiple instance
learning for classifying students in learning management
systems". In this paper, a new attitude built on multiple
instance learning is suggested to predict student’s performance
and to increase the gained results using typical single instance
learning. Multiple instance learning provides a more suitable
and optimized representation that is adapted to available
information of each student and course eliminating the missing
values that make difficult to find efficient solutions when
traditional supervised learning is used. To check the efficiency
of the new proposed representation, the most popular
techniques of traditional supervised learning based on single
instances are matched to those based on numerous instance
learning. They concluded that computational experiments show
that when the problem is regarded as a traditional supervised
learning problem, the results obtained are lower than when the
problem is regarded as a multi-instance problem. Concretely,
the Wilcoxon rank sum test determines with a confidence of
95% that algorithms using multiple instance learning
representation achieve significantly better solutions.
A Comparative Analysis on the Evaluation of Classification
Algorithms in the Prediction of Students Performance is
discussed by Anuratha and Velmurugan in a research work
[16]. The goal of this study provides an analysis of final year
marks of UG degree students using data mining methods,
which carried out in three of the private colleges in Tamil
Nadu state of India. The major objective of this research work
is to apply the classification techniques to the prediction of the
performance of students in end semester university
examinations. Particularly, the decision tree algorithm C4.5
(J48), Bayesian classifiers, k Nearest Neighbor algorithm and
two rule learner’s algorithms namely OneR and JRip are used
for classifying the performance of students as well as to
develop a model of student performance predictors. The result
of this study reveals that overall accuracy of the tested

ISSN: 2278-2419
54
classifiers is above 60%. In addition classification accuracy for
the different classes reveals that the predictions are worst for
distinction class and fairly good for the first class. The JRip
produces highest classification accuracy for the Distinction.
Classification of the students based on the attributes reveals
that prediction rates are not uniform among the classification
algorithms. Also shows that selected data attributes have found
to be influenced the classification process. The results showed
to be satisfactory.
Thus, this section discussed about the methods used for
learning data mining and some other appropriate theme which
are used for the principle of improving both learner
performance as well as the syllabus of a particular institution.
In the largest part of learningsetup, a considerable quantity of
instructor and learner time is committed to activities which
involve assessment by the instructor of learner products or
activities.Consideration is given to outcomes involving
learning approach, inspiration, and reaching. Where promising,
mechanisms are elective that could version for the reported
effects. The end resulting from the charactermeadows are then
merged to manufacture an incorporated sketch with clear
inference for activelearning practice. The mainend is that
classroom evaluation has powerful direct and circumlocutory
Condit, which may be optimistic or pessimistic, and thus merit
very thoughtful arrangement and achievement.
V. CLUSTERING ALGORITHM FOR LDM
Clustering as the name suggests is the process of grouping data
into classes, so that objects within a cluster have high
similarity in comparison to one another, but are very dissimilar
to objects in other cluster. Dissimilarities have been observed
on the basis of attribute value describing the objects often
distance used. It is the process of identification of similar
classes of object. It has been used as a grouping a set of
physical or abstract objects into classes of similar objects. A
cluster is a collection of data objects which are similar to
another within the same cluster and dissimilar to the object in
other cluster. It is an unsupervised learning technique that
shows the natural groupings in data.
Application of k-Means Clusteringalgorithm forprediction of
Students’ Academic Performance was discussed by Oyelade et
al. in [17]. In this paper, they implemented k-means clustering
algorithm for analyzing students’result data in a good manner.
The model was combined with the deterministicmodel to
analyze the students’ results of a private Institution inNigeria
which is a good standard to monitor the evolution ofacademic
performance of students in higher Institution for thepurpose of
making an effective decision by the academicorganizers.It also
enhances the decisionmaking by academic developers to
monitor the candidates’performance semester by semester by
improving on the upcomingacademic results in the subsequent
academic meeting.
A paper titled as "Clustering and sequential pattern mining of
online collaborative learning data" was done by Perera et al.
[18]. They explore how useful reflect information can be
mined via a theory-driven approach and a range of clustering
and sequential pattern mining. The context is a senior software
development project where students use the collaboration tool
track. They mined patterns distinguishing the better from the
weaker groupsand get insights in the success factors. The
results point to the importance of leadership and group
interaction, and givepromising indications if they are
occurring. Patterns indicating good individual practices were
also identified. They found thatsome key measures can be
mined from early data. The results are promising for advising
groups at the start and earlyidentification of effective and poor
practices, in time for remediation. They suggested that this
work will enable the learner to provide regular feedback to
students throughout the semester if their present work
performance is more expected to be associated with positive
ornegative outcomes and where the problems are.A
comparative analysis of various technologies used by different
researchers is given in the table 1, which gives an insight about
the each and every paper taken for analysis in this survey work.
Table 1: Comparative Analysis
Reference Authors Methods
used
Results
1 Dietz-
Uhler et
al.
Learning
analytics
This studies have
indicated individual
faculty can make
use of the data they
have available in
their courses to
affect changeand
improve student
success.
2 Martin et
al.
Bibliometri
c analysis
The study analyzed
by bibliometric
analysis which
technologies were
successful and
became a regular
part of learning
systems
3 Delavari
et al.
HAL The final result from
each model with
various techniques,
presented that they
are all performing
similarly.
4 Peng et al. DMKD This paper
acknowledged eight
main areas of
DMKD
5 Chen et al. BWL The BWL system
was specifically
developed to
integrate the
scaffolding model
with the system.
6 Desmarais
et al.
Cognitive
Modeling
Modeling other key
constructs such as
learner motivation,
emotional and
attention state,
meta-cognition and
self regulated
learning, group
learning, and the

ISSN: 2278-2419
55
recent movement
towards open and
shared learner
models.
7 Aleksandr
aet al.
Tutoring
system
Describing learning
style,learning
characteristics,
preferences and
goals.
8 Saeed et
al.
Learning
styles
Suggested that
learning styles of
today’s learners are
flexible enough to
experience varying
technologies and
their technology
preferences are not
limited to a
particular tool.
9 Ebner et
al.
Microblog
ging
Microblogging
should be seen as a
completely new
form
ofcommunication
that can support
informal learning
beyond classrooms.
10 Yadav et
al.
Decision
tree
The Machine
learning algorithms
such as the C4.5
decision tree
algorithm can learn
effective predictive
models from the
student data
accumulated from
the previous years.
11 Wu et al. Classificati
on
Algorithms
Citedfor
classification,
clustering, statistical
learning, and
association analysis.
12 Huang et
al.
Genetic
algorithm
Suggested three
critical
contributions.
13 Kotsiantis
et al.
Naive
Bayes
Among other
significant
conclusions it was
found that the
proposed algorithm
isthe most
appropriate to be
used for the
construction of a
software support
tool.
14 Ajay
Varma
and Y. S.
Chouhan
Bayesian
Network
The most widely
used classification
techniques in
educational domain
is decision tree.
15 Zafra et Multiple Single instances are
al. instance
learning
compared to those
based on multiple
instance learning.
16 Anuratha.
C and
Velmurug
an. T
C4.5,
Bayesian
classifiers,
kNNalgorit
hm , OneR
and JRip
JRip produces
highest
classification
accuracy
17 Oyelade et
al.
k – mean
clustering
Enhances the
decisionmaking by
academic
developers to
monitor the
candidates’performa
nce semester by
semester by
improving on the
upcomingacademic
results in the
subsequent
academic meeting.
18 Perera et
al.
Collaborati
ve
Learning
Enable the learner to
provide
regularfeedback to
students during the
semester if their
current
workbehavior is
more likely to be
associated with
positive ornegative
outcomes.
VI. CONCLUSION
The recent technologies like educational websites, smart
phones, internets, mobile phones, PDA devises, iPods and
software oriented methods like power point presentations,
social networks and information repositories are create high
impact in the learning as well as teaching process. These
technologies are the main keys of modern world nowadays.
This survey work addresses the significance of LDM in order
to make use of such technology oriented facilities. A number
of articles written by using DM algorithms are reviewed in this
work, which is utilized for the improvement of student’s
performance. Based on the observation, many DM algorithms
are suitable for LDM. From the various researchers’
perspectives, it is enlisted that many advanced technologies are
effectively used for learning process. Also, most of the recent
teaching methodologies are effectively created high impact in
improving the personally as well as the performance of
students. Most of the research work has new methods and
patterns to maximize the student’s performance through LDM
techniques. Some of the clustering algorithms and
classification algorithms like ID3 and C4.5 are used to identify
the various categories of students’ performances. For the
chosen data concept by the various researchers, the behavior
and performance of both the categories of algorithms differ.
Many research works finds that C4.5 classification algorithm
stamps its superiority in classifying student categories. Thus,

ISSN: 2278-2419
56
this work concludes that the recent technologies are more
useful and a gift for quick learning with less cost.
References
[1] Dietz-Uhler, Beth, and Janet E. Hurn, "Using learning
analytics to predict (and improve) student success: A
faculty perspective", Journal of Interactive Online
Learning, Vol. 12, No. 1, 2013, pp. 17-26.
[2] Martin, Sergio, Gabriel Diaz, ElioSancristobal, Rosario
Gil, Manuel Castro, and Juan Peire, "New technology
trends in education: Seven years of forecasts and
convergence", Computers & Education, Vol. 57, No. 3,
2011, pp. 1893-1906.
[3] Delavari, Naeimeh, SomnukPhon-Amnuaisuk, and
Mohammad Reza Beikzadeh, "Data mining application in
higher learning institutions", Informatics in Education-
International Journal,Vol. 7, No. 1, 2008, pp. 31-54.
[4] Peng, Yi, Gang Kou, Yong Shi, and Zhengxin Chen, "A
descriptive framework for the field of data mining and
knowledge discovery", International Journal of
Information Technology & Decision Making,Vol. 7, No.
04, 2008, pp. 639-682.
[5] Chen, Yuh-Shyan, Tai-Chien Kao, and Jay-Ping Sheu, "A
mobile learning system for scaffolding bird watching
learning", Journal of Computer Assisted Learning Vol. 19,
No. 3, 2003, pp. 347-359.
[6] Desmarais, Michel C., and Ryan SJ d Baker, "A review of
recent advances in learner and skill modeling in intelligent
learning environments", User Modeling and User-Adapted
Interaction, Vol. 22, No. 1-2, 2012, pp. 9-38.
[7] Klašnja-Milićević, Aleksandra, BobanVesin,
MirjanaIvanović, and ZoranBudimac, "E-Learning
personalization based on hybrid recommendation strategy
and learning style identification", Computers & Education,
Vol. 56, No. 3, 2011, pp. 885-899.
[8] Saeed, Nauman, Yun Yang, and SukuSinnappan,
"Emerging Web Technologies in Higher Education: A
Case of Incorporating Blogs, Podcasts and Social
Bookmarks in a Web Programming Course based on
Students' Learning Styles and Technology
Preferences", Educational Technology & Society, Vol. 12,
No. 4, 2009, pp. 98-109.
[9] Ebner, Martin, Conrad Lienhardt, Matthias Rohs, and Iris
Meyer, "Microblogs in Higher Education–A chance to
facilitate informal and process-oriented
learning?", Computers & Education, Vol. 55, no. 1, 2010,
pp. 92-100.
[10]Yadav, Surjeet Kumar, and Saurabh Pal, "Data mining: A
prediction for performance improvement of engineering
students using classification", World of Computer Science
and Information Technology Journal (WCSIT), Vol. 2,
No. 2, 2012, pp. 51-56.
[11]Wu, Xindong, Vipin Kumar, J. Ross Quinlan,
JoydeepGhosh, Qiang Yang, Hiroshi Motoda, Geoffrey J.
McLachlan,. "Top 10 algorithms in data
mining", Knowledge and information systems, Vol. 14,
No. 1, 2008, pp. 1-37.
[12]Huang, Mu-Jung, Hwa-Shan Huang, and Mu-Yen Chen,
"Constructing a personalized e-learning system based on
genetic algorithm and case-based reasoning
approach", Expert Systems with Applications, Vol. 33,
No. 3, 2007, pp. 551-564.
[13]Kotsiantis, S., KiriakosPatriarcheas, and M. Xenos, "A
combinational incremental ensemble of classifiers as a
technique for predicting students’ performance in distance
education", Knowledge-Based Systems, Vol. 23, No. 6,
2010, pp. 529-535.
[14]Varma, Ajay, and Y. S. Chouhan. "Recent Methodologies
for Improving and Evaluating Academic Performance",
International Journal of Scientific Research in Computer
Science and Engineering, Vol. 3, Issue 2, 2015, pp. 11-16.
[15]Zafra, Amelia, Cristóbal Romero, and Sebastián Ventura,
"Multiple instance learning for classifying students in
learning management systems", Expert Systems with
Applications, Vol. 38, No. 12, 2011, pp. 15020-15031.
[16]C. Anuratha and T.Velmurugan, “A Comparative Analysis
on the Evaluation of Classification Algorithms in the
Prediction of Students Performance”, Indian Journal of
Science and Technology, Vol. 8, Issue 15, 2015, DOI:
10.17485/ijst/2015/v8i15/74555
[17]Oyelade, O. J., O. O. Oladipupo, and I. C. Obagbuwa,
"Application of k Means Clustering algorithm for
prediction of Students Academic
Performance", International Journal of Computer Science
and Information Security, Vol. 7, No. 1, 2010, pp. 292-
295.
[18]Perera, Dilhan, Judy Kay, Irena Koprinska, KalinaYacef,
and Osmar R. Zaïane, "Clustering and sequential pattern
mining of online collaborative learning data", Knowledge
and Data Engineering, IEEE Transactions, Vol. 21, No. 6,
2009, pp. 759-772.

Technology Enabled Learning to Improve Student Performance: A Survey

More Related Content

Similar to Technology Enabled Learning to Improve Student Performance: A Survey (20)

More from IIRindia (20)

Recently uploaded (20)

Technology Enabled Learning to Improve Student Performance: A Survey