Cognitive Computing and Education and Learning

International Journal of Trend in Scientific Research and Development (IJTSRD)
Volume 6 Issue 3, March-April 2022 Available Online: www.ijtsrd.com e-ISSN: 2456 – 6470
@ IJTSRD | Unique Paper ID – IJTSRD49783 | Volume – 6 | Issue – 3 | Mar-Apr 2022 Page 1628
Cognitive Computing and Education and Learning
Latifa Rahman
Department of Administrative and Instructional Leadership,
School of Education, St. John's University, New York, USA
ABSTRACT
Its enormous potential in learning spurs Cognitive Computing. The
overreaching purpose here is to devise computational frameworks to
help us learn better by exploiting the learning process and activities.
The research challenge recognized the broad spectrum of human
learning, the complex and not fully understood human learning
process, and various learning factors, such as pedagogy, technology,
and social elements. From the theoretical point of view, Cognitive
Computing could replace existing calculators in many applications.
This paper focuses on applying data mining and learning analytics,
clustering student modeling, and predicting student performance
when involved in the education field with possible approaches.
KEYWORDS: Cognitive Computing, Learning Process, Education
How to cite this paper: Latifa Rahman
"Cognitive Computing and Education
and Learning"
Published in
International Journal
of Trend in Scientific
Research and
Development (ijtsrd),
ISSN: 2456-6470,
Volume-6 | Issue-3,
April 2022, pp.1628-1632, URL:
www.ijtsrd.com/papers/ijtsrd49783.pdf
Copyright © 2022 by author (s) and
International Journal of Trend in
Scientific Research and Development
Journal. This is an
Open Access article
distributed under the
terms of the Creative Commons
Attribution License (CC BY 4.0)
(http://creativecommons.org/licenses/by/4.0)
INTRODUCTION
Cognitive computing is the new wave of Artificial
Intelligence (AI), relying on traditional techniques
based on expert systems and exploiting statistics and
mathematical models. It uses computerized models to
simulate the human thought process in complex
situations where the answers may be ambiguous and
uncertain (Bernard, 2016). Cognitive computing
systems can be regarded as "more human" artificial
intelligence (Mauro C, Paolo M. Lidia S., 2016). The
overreaching goal here is to devise computational
frameworks to help us learn better by exploiting the
learning process and activities. There are two
essential aspects of it- the mechanisms or insights
about how we know and the external manifestations
of our learning activities (Lake et al., 2015). The
goals of cognitive computing use self-learning
algorithms that use data mining, pattern recognition,
and natural language processing can mimic how the
human brain works. In education, cognitive
computing refers to reasoning, language processing,
machine learning, and human capabilities that help
everyday computing solve problems and analyze data.
By learning patterns and behaviors and becoming
more intelligent, a computer system challenges
complex decision-making processes. It can identify
three main areas in which cognitive computing will
cover a significant role: advancements in computation
capabilities, human-computer interactions and
communications, and the evolution of the Internet of
Things (loT) (Mauro C, Paolo M. Lidia S., 2016).
Cognitive computing successfully deals with complex
tasks such as natural language processing and
classification, data mining, and knowledge
management; hence cognitive systems can perform
sophisticated duties. It is a relationships extraction
from unstructured corpus, speech-to-text, and text to
speech conversions, pattern recognition, computer
vision, and machine learning which involve research
areas based on human-like reasoning techniques.
Cognitive computing systems owe their ability to a
large amount of data analysis and process to feed the
machine learning algorithms. For example, popular
technology Artificial Intelligence is employed in
search engines;it provides in a seamless manner entity
extraction, clustering, and classification and pulls
back only information that is relevant to the users,
based both on personal data and on the application of
patterns. (Pazzani & Billsus, 2007).
IJTSRD49783

International Journal of Trend in Scientific Research and Development @ www.ijtsrd.com eISSN: 2456-6470
Cognitive computing fosters new ways of interaction
between humans and computers. Since cognitive
computing simulates human reasoning processes by
translating them into suited templates, it can help
machines learn and teach humans new concepts and
behaviors. Such intelligent systems could be used in
training and customization or other activities
requiring data analytics to improve processes and
products (Earley, 2015).It generates big data in
education and learning through activities, presenting
enormous potential and a great challenge. Big data
are typically characterized by five V's-volume (data
are large scale), variety (data come in many different
forms), velocity (data have some elements of
uncertainty), and value (extracting actionable
intelligence). The first four V" are visible in
education and learning application settings. For
example, a learning Management system (LMS) like
Moodle (2016) or any Massive Open line Course
(MOOC) generates a considerable volume of data.
Moreover, the data come in various forms, such as
student answers to quantitative questions and essay-
type questions, which are verydifficult. The cognitive
computing community has embarrassed the
emergence of Big Data, thereby shaping up several
subfields relevant to education and learning. From the
e-learning point of view, it reported some experiences
that witnessed how cognitive computing can be an
accelerator for students' achievements and valuable
support for the teachers. In particular:
1. Integrating cognitive computing services in
software applications can enormously enhance
students' performance in computer science
classes.
2. Studying cognitive computing behavior can lead
to significant results in AI-related studies.
3. Using a cognitive computing layer for digital
interactions with students enhances their
performance and eases the teachers' jobs in
managing classes and learning materials.
Educational Data Mining
The increasing use of technology in educational
systems has presented a large amount of data. EDM
provides a significant amount of essential data
(Mostow. J & Beck. J, 2006) and offers a clearer
picture of learners and their learning process.
Advances have inspired EDM in data mining and
machine learning. The overreaching goal is to help
teachers, students, and other stakeholders achieve
their respective objectives by utilizing Big Data in
education. The International Educational Datamining
Society (2016) has defined the field as "concerned
with developing techniques for discovering the
unique and increasingly large-scale data that come
educational settings, and using those methods to
understand students better, and the settings they learn
in."
1. Educational Data Mining allows consumers to
extract information from student data. This
information can be used in different ways, such as
validating and evaluating an educational system,
improving the quality of teaching and learning
practices, and laying the groundwork for a more
effective learning process (Romero. C, Ventura
S., & Bra De. P., 2004). Baker (2009) suggested
four key areas of EDM application: improving
student models, improving domain models,
studying the pedagogical support provided by
learning software and conducting scientific
research on learning and learners. Five
approaches are available: prediction, clustering,
relationship mining, the distillation of data for
human judgment, and discovery with models.
2. EDM tasks mention four different areas of
applications that deal with the assessment of (a)
students learning performance, (b) course
adaptation and learning recommendations to
customize students learning based on individual
students' behaviors, (c) developing a method to
evaluate materials in online courses, (d)
approaches that use response from students and
teachers in e-learning courses, and it detects the
models for uncovering student learning behaviors
(Castro, 2007).
Learning Analytics
Learning analytics represents data about learners to
develop a learning environment where a new model
makes a difference through which teachers can
understand education. The first International
Conference on Learning Analytics and Knowledge
(LAK) was held in 2011. At that time, the LA
community identified the LA field as Learning
Analytics is the measurement, collection, analysis,
and reporting of data about learners and their contexts
to understand and optimize learning and the
environments in which it occurs" (Long and Siemens,
2011).
Learning analytics is the application of these Big Data
techniques to improve learning. Learning analytics is
currently a fixture in educational horizon-scanning
reports (Johnson et al., 2011; Johnson, Adams, and
Cummins, 2012; Sharples et al., 2012) and a raft of
other publications aimed at practitioners and aspiring
practitioners from organizations concerned with
technology in education, such as Educause, JISC and
SURF. For instance, Blackboard, Desire2Learn,
Instructure, and Tribal have all released tools, and
there is also an activity in the Moodle community.

The high-profile providers of Massively Open Online
Courses (MOOCs)- Coursera, Udacity, and edX- use
analytics tools to inform their practice.
A key concern in learning analytics is using the
insights gathered from the data to make interventions
to improve learning and generate "actionable
intelligence" (Campbell, DeBlois, and Oblinger,
2007), which informs appropriate interventions.
Compared to Educational data mining, learning
analytics embodies a broader umbrella of learning
settings, tools, techniques, human and social factors,
and applications. Educational data mining is focused
on automation and is frequently concerned with
unearthing hidden patterns from data, whereas
Learning analytics is more holistic and human-centric
(Siemnes and Baker, 2012). In contrast, learning
analytics is inherently an area of analytics, and
therefore various analytics instruments, such as
discourse analysis and social network analysis, are
more important in learning analytics and educational
data mining.
Clustering and Student Modeling
Clustering is used to operate data into different
groups on certain standard features. Unlike the
classification method, in clustering, the data labels are
unknown. The clustering method gives the user a
broad view of what is happening in that dataset.
Clustering is sometimes an unsupervised
classification because class labels are unknown
(Fayyad, 1996). The number of groups can be
predefined in the clustering methods. Clustering is a
common technique where EDM for aggregating
student data to examine student behavior. An
evolutionary clustering technique for sequential
student data (Klingeler et al., 2016). Compared to
previous works, their approach improves clustering
stability for noisy data.
Student modeling is the structure of a qualitative
representation that accounts for student behavior in a
system's knowledge background. These three – the
student model, the student behavior, and the
background knowledge- are the essential elements of
student modeling. Student behavior refers to a
student's observable response to a particular stimulus
in each domain that, together with the inspiration,
serves as the primary input to a student modeling
system (Raymund Sison & Masamichi Shimura,
2008). Moreover, another central problem in EDM is
student modeling. When using data from Duolingo
(2016), Streeter (2015) has used probabilistic mixture
models to capture the learning curves of language
learners. An individual learning curve represents error
percentages over time. Streeter's work generalizes
knowledge tracing and offers an elegant probabilistic
model for modeling learning curves. The model
parameters have been learned using the well-known
expectation-maximization algorithm. Based on the
large-scale Duolingo dataset, the mixture model
outperforms many previous approaches, including
popular cognitive models like the Additive Factor
Model (AFM) (Cen et al., 2006).
Predicting Student Performance
Prediction of students' performance has become an
urgent desire in most educational entities and
institutes. That is essential to help at-risk students and
assure their retention, provide excellent learning
resources and experiences, and improve university
ranking and reputation. Furthermore, it has been a
famous line of research in EDM based on various
factors. Student performance has been measured in
specific disciplines or topics, such as algebra (Stapel
et al., 2016) and programming in Java (Tomkins et
al., 2016).
Student records analysis for startups to medium-sized
institutes or schools, like the British University in
Dubai, which has small student records, has never
been explored in the educational or learning analytics
domain. (Ingrassia & Morlini, 2005; Pasini, 2015).
Additionally, most researchers aimed to classify or
predict; researchers spent many efforts extracting the
essential indicators that could be more useful in
constructing reasonably accurate predictive models.
They will either use features ranking algorithms or
look at the selected features while training the dataset
on different machine learning algorithms.
(Comendador, Rabago, & Tanguiling, 2016; Mueen,
Zafar, & Manzoor, 2016).
Many students received coaching while taking
MOOC, and coaching students performed better than
the independent students in the MOOC (Tomkins et
al., 2016). Another study shows that the context of
MOOCs predicts student dropout and proposes an
intervention study (Whitehill et al., 2015). Student
dropout is a widespread phenomenon in MOOCs
(Onah et al., 2014; Riverd, 2013). The post-course
survey is ineffective in detecting the reasons for the
dropout since the response rates for such surveys are
usually very low. The techniques for detecting student
dropout and prose an intervention strategyin the form
of early surveys to retain students. They used the
HarvardX MOOC educational program to evaluate
the effectiveness of their approach to knowing more
about dropouts.
Conclusion
Technology is valuable day by day. The increase in
education generates a large amount of data every day,
which has become an aim for many academics
worldwide; educational mining is proliferating. And it

has the advantage of containing new algorithms and
techniques developed in different data mining areas
and machine learning. The interaction between
academia and industry is a remarkable feature of
cognitive computing, especially in its applications in
education and learning. For example, companies like
IBM embrace cognitive computing to harness the
power of Big Data in multiple application areas,
including education (Davis, 2016). Learning analytics
is the inspiration of teachers and students to
understand the wealth of data related to their learning
in the educational platform. Engaging in the process
is a way of taking concern of the economic framing
that can be supplemented with respect for knowledge.
The focus on the data alone is not sufficient: to
achieve institutional transformation, learning
analytics data need to be presented and contextualized
in various ways that can drive organizational growth
(Macfadyen and Dawson, 2012). Soon, cognitive
computing technology and related applications will be
possible in a complex ecosystem where the valuable
data available within the education system, including
institutions and municipalities, can be exchanged
between applications and organizations seamlessly
and transparently, which will help students learn more
in future.
References
[1] Bernard, M. (2016). What Everyone Should
Know About Cognitive Computing. Forbes.
[2] R. S. Baker and K. Yacef. (2009)"The state of
educational data mining in 2009: A review and
future visions," JEDM-Journal of Educational
Data Mining, vol. 1, no. 1, pp. 3–17.
[3] C. Romero, S. Ventura, and P. De Bra
(2004)"Knowledge discovery with genetic
programming for providing feedback to
courseware authors," User Modeling and User-
Adapted Interaction, vol. 14, no. 5, pp. 425–
464.
[4] Campbell, John P., Peter B. De Blois, and
Diana G. Oblinger. (2007). "Academic
Analytics: A New Tool for a New Era."
Educause Review 42 (4): 4057. Retrieve from
http://www.educause.edu/ero/ article/academic-
analytics-new-tool-new-era.
[5] Comendador, B. E. V., Rabago, L. W., &
Tanguilig, B. T. (2016). An educational model
based on knowledge discovery in databases
(KDD) to predict learner's behavior using
classification techniques. In 2016 IEEE Int.
Conf. Signal Process. Common. Comput, (pp.
1–6).
[6] Cen, H., Koedinger, K., Junker, B., (2006).
Learning factors analysis- a general method for
cognitive model evaluation and improvement.
In: Intelligent tutoring systems, Springer, New
York, NY, pp. 164-175
[7] Davis, K., (2016). IBM launched the industry's
first consulting practice dedicated to cognitive
business. http://www-
03.ibm.com/press/us/en/pressrelease/47785.wss
[8] Duolingo (2016). A game-based approach to
learning natural languages.
https://www.duolingo.com
[9] Earley, S. (2015), Executive roundtable series:
machine learning and cognitive Computing, IT
Professional, 17(4), 56-60.
[10] Ingrassia, S., & Morlini, I. (2005). Neural
network modeling for small
datasets. Technometrics
[11] J. Mostow and J. Beck (2006)"Some useful
tactics to modify, map and mine data from
intelligent tutors," Natural Language
Engineering, vol. 12, no. 02, pp. 195–208.
[12] Johnson, L., R. Smith, H. Willis, A. Levine,
and K. Haywood. (2011). The 2011 Horizon
Report. Austin, TX: The New Media
Consortium.http://net.educause.edu/ir/library/p
df/hr2011.pdf
[13] Johnson, L., S. Adams, and M. Cummins.
(2012). The NMC Horizon Report: 2012
Higher Education Edition. Austin, TX: The
New Media Consortium.
http://www.nmc.org/pdf/2012- horizon-report-
HE.pdf.
[14] Klinger, S., Kaser, T., Solenthaler, B., Gross,
M., (2016). Temporarily coherent clustering of
student data. In: Proceedings of the 9th
International Conference on Educational Data
Mining, International Educational Data Mining
Society, 102-109.
[15] Long, P., Siemens, G. (Eds.), (2011). LAK'11:
Proceedings of the 1st
International Conference
on Learning Analytics and Knowledge, Banff,
Alberta, Canada. ACM, New York, NY. ISBN
978-1-4503-0944-8.
[16] Mauro C, Paolo M. Lidia S., (2016). Cognitive
computing in education. Journal of e-learning
and knowledge society. Vol. 12, n.2
[17] Macfadyen, Leah, and Shane Dawson. (2012).
"Numbers Are Not Enough. Why e-Learning
Analytics Failed to Inform an Institutional

Strategic Plan." Educational Technology and
Society 15 (3): 149163.
http://www.ifets.info/journals/15_3/11.pdf
[18] Sharples, M., Patrick M., Martin W., Rebecca
F., Elizabeth F., Tony H., Yishay M., Mark G.,
& Denise W.,(2012). Innovating Pedagogy.
[19] Stapel, M., Zheng, Z., Pinkwari, N., (2016). An
ensemble method to predict student
performance in an online math learning
environment. In: Proceedings of the 9th
Ming, International Educational Data Mining
Society, 231-238.
[20] Raymund S., &Masamichi S., (1998). Student
Modeling and Machine Learning. International
Journal of Artificial Intelligence in Education
(IJAIED), 9, pp.128-158. final-00257111f
[21] Open University Innovation Report 1. Milton
Keynes: The Open University. http://
www.open.ac.uk/personalpages/mike.sharples/
Reports/Innovating_Pedagogy_report_July_
2012.pdf.
[22] Olsen, J.K., Aleven, V., Rummel, N., (2015).
Predicting student performance in a
collaborative learning environment. In:
Proceedings of EDM.
[23] Onah, D.F., Sinclair, J., Boyatt, R., (2014).
Dropout rates of massive open online courses:
behavioral patterns. IN: Proceedings of the 8th
Mining, International Educational Data Mining
Society, 211-217.
[24] Rivard, R., (2013). Measuring the MOOC
Dropout Rate. Inside Higher Ed, 8,
https://www.
insidehighered.com/news/2013/03/08/researche
rs-explore-who-taking-MOOCs-and-why-so-
manydropout
[25] Siemens, G., Baker, R., (2012). Learning
analytics and educational data mining: towards
communication and collaboration. In:
proceeding of the 2nd
International conference
on learning analytics and knowledge. LAK'12.
Vancouver, British Columbia, Canada. ACM,
New York, NY, pp. 252-254.
[26] Streeter, M., (2015). Mixture modeling of
individual learning curves. In: International
Conference on Educational Data Mining.
[27] Tomkins, S., Ramesh, A., Getoor, L., (2016).
Predicting post-test performance from student
behavior: a high school MOOC case study. In:
Proceedings of the 9th
International Conference
on Educational Data Mining, International
Educational Data Mining Society, 239-246.
[28] Pazzani, M.J. and Billsus, D. (2007), Content-
based recommendation systems, in The
Adaptive Web, P. Brusilowsky, A. Kobsa and
W. Nejdl (Eds.), LNCS 4321, 325- 341,
Springer-Verlag, Berlin Heidelberg.
[29] Pasini, A. (2015). Artificial neural networks for
small dataset analysis. Journal of Thoracic
Disease.
[30] U. Fayyad, G. Piatetsky-Shapiro, & P. Smyth
(1996)."The KDD process for extracting useful
knowledge from volumes of data,"
Communications of the ACM, vol. 39, no. 11,
pp. 27–34.

Cognitive Computing and Education and Learning

More Related Content

Similar to Cognitive Computing and Education and Learning (20)

More from ijtsrd (20)

Recently uploaded (20)

Cognitive Computing and Education and Learning