A Brief Review of using LMS in Computer Science Learning
Fadoua Koucham, Youn
`
es El Bouzekri El Idrissi and Ayoub Ait Lahcen
Engineering sciences laboratory, National School of Applied Sciences, Ibn Tofail University, Kenitra, Morocco
Keywords:
E-learning, Computer Science Learning, LMS, Intelligent Tutoring System
Abstract:
The world of technology is expanding at a breakneck pace, and the ability of humans to learn and progress has
a significant impact on attaining a high degree of knowledge. Therefore, humans seek to change and value the
systematic tools used by having a good learning acquisition. Thus far, various strategies have been utilized in
the educational system to facilitate and maintain a strong knowledge of student learning behaviour. Especially
in the e-learning system, which appreciates considerable importance to the student community and has been
the subject of an extensive investigation by developers and researchers to make it more resilient, accessible,
and motivating for students to learn. In light of this, this paper aims to critically review different approaches
to implementing the development of the LMS system for computer science (CS) students.
1 INTRODUCTION
In the history of the development education
system, e-learning has been critically impacting
the improvement of student knowledge by getting
courses in the distance. Thus, some institutes adopt
blended learning (Patel et al., 2013), which combines
face-to-face with distance learning, to offer the
student the most ability to comprehend the subject.
Therefore, one of the most popular systems used
in e-learning education is the Learning Management
System (LMS): a software application responsible for
all learning areas for instructors and students; it offers
essential tools such as downloading courses, submit
and return assignments to acquire the theoretical
concept of the subject (Yulianto et al., 2016) also
it provides directly the creation and delivery of
content by the teachers, as well as the monitoring and
evaluation of student engagement and performance.
Such as Moodle, the widespread LMS use by most
education institutes that adopt distance learning, is
open-source and free. Still, unfortunately, this type
of system not offering the student the interactive part
to practice the new concept learned (Al-Khanjari and
Al-Roshdi, 2015).
This issue considers a gap for student learning,
who have the habit of getting the basic concept
of subject and practising it to have a good
comprehension of the course, and this impact all
subject mainly a computer science student which they
must have a practising part, considering a computer
science must adopt three basic steps to acquire
knowledge: cognitive, constructive, and socially
situated learning(Yulianto et al., 2016).
• Cognitive: Understanding different theoretical
programming languages with prerequire
knowledge to facilitate the comprehension
of the new concept (Yulianto et al., 2016).
• Constructive: Making an actual application
to improve the excellent learning theoretical
programming language (Yulianto et al., 2016).
• Socially situated learning: Considering as social
interaction, by using different online tools such as
forum discussion, email, social networks, or even
a real-life face-to-face sharing knowledge, which
allows exchanging cognition to solve a problem
and lead to improving knowledge (Muhisn et al.,
2019).
This paper surveys recent studies on the
employment of learning management systems in
computer science learning. The first section of
this paper will examine the literature review by
introducing two different ways of ensuring education
for computer science students using the standard and
the adaptive LMS, then a conclusion with a mention
of our future research goal.
196
Koucham, F., El Bouzekri El Idrissi, Y. and Ait Lahcen, A.
A Brief Review of using LMS in Computer Science Learning.
DOI: 10.5220/0010730900003101
In Proceedings of the 2nd International Conference on Big Data, Modelling and Machine Learning (BML 2021), pages 196-200
ISBN: 978-989-758-559-3
Copyright
c
 2022 by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved

2 LITERATURE REVIEW
More recent attention has focused on providing the
perfect approach of implementing a learning system
that improves online education for a computer science
student.
It considered many different methods to transform
traditional LMS learning into a system that gives
a student interaction possible, powerful, and
personalized.
2.1 Standard Learning Management
System in Computer Science
Learning
Researchers (Al-Khanjari and Al-Roshdi, 2015)
have introduced two approaches implemented to the
standard LMS to ensure practical usage. So that
the students would be able to solve online exercise
problems, watch a video course, compile code, and
display the results into different CS courses; the study
is based on Moodle LMS since a large community use
it, namely:
• Connect extern tools, an existing application, or
a new application developed by any language
with the LMS system by a button link integrated
inside the platform, facilitating users to access
the extern desired tools inside Moodle. This
approach is realizable by a technology combined
with Moodle, the learning tool Interoperability
LTI.
This approach has multiple advantages, such as
reducing the time of execution of the platform
since different manipulation will be outside,
and the disadvantage of this method is limited
functionality.
• Make an SOA communication between differents
tools developed as service (SAAS), registering
into the service registry UDDI, and implemented
into Moodle using LTI technology.
Furthermore, motivation is an essential aspect of
improving the active engagement of students learning
a programming language into standard LMS in a
computer science study.
Thus, an early example of research into (Almeida
et al., 2017) has implemented a new methodology of
learning programming using a robot. The main idea
is to make an active part of controlling a robot in the
distance; by executing code inside the LMS system,
moving it from one destination to another. The
students can access the robotic experiments according
to their scheduling time on a specific day; the program
offers five challenges—the robot has been situating in
the laboratory, connected to the server by Bluetooth.
A camera associated with a server by IP address
shows the robot’s movement in the LMS interface.
When the user sends the code to the server, the robot
agent looks for the programming code and generates
the execution file using the NXT-Python program. If
there is no error, the running program controls the
robot remotely.
Another way to improve student motivation is
using the Multimedia Educational Resource for
Learning and Online Teaching concept (MERLOT).
An online repository that englobes digital resources;
learning objects (LOs): like images, tutorials,
simulation, quiz, test, presentation and all other tools
helping to create a complete unit of learning regroups
by categories, and which allow the registered user to
rats in each LOs, and making a private collection.
That aid improves the MERLOT repository by the
user and has visualization into digital resources that
have less interaction by the student, which will
help the organization make it enhance in the future
(Alharbi et al., 2011). The MERLOT concept can
easily combine with the Open Educational Resources
(OER) projects such as LMS (Gunarathne et al.,
2020).
2.2 Personalized Content in Learning
Management System
A new approach proposed by (Thamarai Selvi and
Panneerselvam, 2012) was integrating tools and
material into the LMS system that improves self-
regulated learning within the student’s knowledge
level, based on adaptive learning object (ALOB), that
allows generating personalized content.
The implementation of this approach focused on
learning the C language. The main idea is to
classify the course into six-level; each part provides
appropriate content based on the student’s level,
relying on different student information collected.
The architecture focus on creating multiple web
service-oriented within (SOAP) protocols. Each web
service has a mean objective such as:
• Self-monitoring: Register the accomplished
courses and the time spent at each level.
• Self-assessment: Render the teacher questions to
the student and save the return response.
• Feedback: Automatically proposed feedback to
the student, which reduces the teacher effort,
based on the response assessment and the
registration of activities.
A Brief Review of using LMS in Computer Science Learning
197

2.3 Learning Management System with
Intelligent Tutoring System
2.3.1 Standard Intelligent Tutoring System
Among the outgrowth technic that has been evolving
of the personalized learning system, since the
appearance of Artificial Intelligence (AI) in the
educational domain in the 1970s, is the birth of
a new concept, the Intelligent Tutoring System
(ITS)(Almasri et al., 2019).
Intelligent tutoring systems are computer
programs that combine three crucial disciplines:
education or theorists discipline, intelligent artificial,
and psychology or cognition discipline. The
ITS strives to provide learners with instant and
personalized education or feedback, usually without
the need for the teacher’s intervention. All the
procedurals began in the 1950s with developing the
first model of this system known as Computer-Aided
Instruction. The fundamental phase to be recognized
in systems has been the teacher’s experience,
memory in a pre-stored structure element named
frames, produced by the specialist instructor and
exposed to the student following specific conditions.
But such absolute representation of cognition has
since been acknowledged as ineffectual; they could
not afford valuable feedback or individualization.
It led in the 1970s to combine Computer-Aided
Instruction with Artificial Intelligence and consider
different information about a student represented as a
psychologist discipline (Nwana, 1990).
There was a significant accord in the literature
that ITSs consists of at least four primary models:
knowledge model, also known as a domain or expert
model, pedagogical model, student model and user
interface model (Almasri et al., 2019), Each of those
models has a meaningful role and implementation.
• Knowledge model: Acts as the reference of
knowledge to present to the student (Nwana,
1990).
• Student model: It consists of a dynamic display of
student’s knowledge and abilities (Nwana, 1990).
• Pedagogical model: It strictly links to the student
model, deciding which educational activities to
offer based on information about the student and
its tutorial intent structure (Nwana, 1990).
• User interface model: Allow interaction between
ITS system and the student (Almasri et al., 2019).
Despite the various changes and updates of ITSs
architecture, they act in the same way. According
to (Santos and Jorge, 2013), ITS design support two
primary task loops: The inner and outer loop:
• The inner loop assures the student’s assistance
in the process of direct solving problems
by proposing hints and providing rapid and
automatization of the adaptive feedback, which
lead a positive satisfaction returning in the
interactive learning system (Riaz et al., 2019),
through evaluating student competence registered
on the student model.
• The outer loop executes the task that the student
should practice for the next step; the decision
made is according to the student’s knowledge.
The most important responsibility of an ITS was
to assist a student in the problem-solving process.
The required knowledge has expected to learn outside
of the system. With the advancement of computer
capabilities, many ITS developers have found it
feasible to combine an ITS with instructional content
in an electronic format.
According to (Alkhatlan and Kalita, 2018),
Several influential and successful ITSs realised in
recent years, including:
• Affective Tutoring Systems (ATS): ATS are
the ITSs that are capable of recognizing
human emotions in real-time. These devices
are responsible for identifying physical signals
such as facial pictures, sounds, heart speed,
pressure and pressure levels. However, recent
learning theories have proved a connection
between emotions and education, claiming that
knowledge, sentiment and motivation, are the
three components of education.
• Cultural Awareness in Education: It considered
the various changes applied to the ITS in the
optics of learning technologies systems thinking
existence of multiple cultures.
• Game-based Tutoring Systems: Students play
an instructional game that successfully mixes
gaming methods with curriculum-based materials
rather than learning a subject traditionally.
Students learn better when they are having fun and
are involved in the learning process.
• Adaptive Intelligent Web Based Educational
System (AIWBES): It is advanced research
on adaptive educational hypermedia, which
combines ITSs with educational hypermedia.
• Data mining: Data mining is the process of
examining large volumes of data to extract and
identify valuable information. Data mining
integrate into ITSs for various goals, such
as catching student effects and automatically
determining a partial problem space from logged
user interactions.
BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)
198

• Collaborative Learning: They incorporate
collaborative learning into tutoring systems to
demonstrate the benefits of student engagement
during problem-solving. So that students could
study in groups by asking questions, clarifying
and defending their opinions, and presenting their
information.
• Authoring Tools: ITS research organisations
have been interested in creating ITSs easier for
designers and teachers by making ITS authorship
more accessible. Authoring tools in the ITS area
is classifying into several categories, including the
required programming skills and those that do not,
as well as pedagogy-oriented and performance-
oriented tools.
2.3.2 Intelligent Tutoring System Architecture
in Computer Science Learning
Implementing the ITS approach to assure adaptive
learning in computer science significantly impacts
analyzing learning within a student. Thus, ITS
architecture has known several updates to solve
different needs indoors to improve the computer
science study. Namely, (Wang et al., 2020) has
proposed a novel approach to help students generate
a good response program over a specific problem.
A classical method was to introduce the Online
Judge (OJ). This system executes a response code
of a problem and gives two output feedback: if the
response code is correct or incorrect, it did not give
more details or suggestions. Although, this approach
did not help the beginner programmer student
enough, which needs more override proposition
within the output feedback. Thence, the novel
ITS consist of integrating the following component:
error repair, Frontend using VueJs Framework,
Backend implementing Django Framework, Postgres
database, code classification by using CLARA engine
allows classifying the similar proposing response of
the same problem, knowledge tracing to identify
level knowledge student. It categorized into four
principal parameters: two parameters according to the
knowledge parameters and the two others from the
performance. Therefore, the new implementations
of the ITS have allowed having hinted feedback
about error codes sent by students within the given
problem or even a repair answer, which will help
students correctly introduce a new response and
acquire analyses behaviour of the programming.
Moreover, unless the availability of multiple
projects that support integrating personalized learning
into LMS, such as GRAPPLE and T-MAESTRO
projects. Hence, they use a nonstandard external
database and setup to assure adaptation (Santos
and Jorge, 2013). Therefore, a researcher (Santos
and Jorge, 2013) has investigated into implementing
two novel concepts into ITS architecture to allow
standardization and facilitation of implementation
ITS into an open-source project such as OERs,
personalized, and intelligent LOs, namely:
• Atomic tutors (AT): Equivalent to a small
educator system, representing a specific task
within a topic, which held only on performing the
inner loop.
• Molecular tutors (MT): Implement the outer loop,
which picks up a specific AT that should be
allowed to a learner at a distinct moment by using
the student model to select the appropriate task.
Thus one particular MT represents a complete ITS
for a specific topic.
Foremost existing researchers on ITS system for
computer science focus on teaching programming
languages to the students (Crow et al., 2018); by
apprenticeship standard programming language based
on the one-one learning such as C++, JAVA, C
sharp, database, PHP web programming, while other
ITSs systems have supported collaborative learning,
known by the computer-supported collaborative
learning (CSCL), to apprenticeship UML modelling
within groups community to motivate the learning
processing within a student by implementing the
constraint-Based Modeling (CBM) (Almasri et al.,
2019).
Although ITS support various features, which
are classifying within six essential approaches:
example, simulation, dialogue, program, feedback,
collaboration (Nesbit et al., 2015):
• Pedagogical assistant: The character appearing
on the platform is usually presented as an avatar
animated, leading to show notifications. It allows
the student to have cognition about different
messages delivered by the ITS (Nesbit et al.,
2015).
• Feedback: Proposing feedbacks depending on
student response(Crow et al., 2018).
• Hints: Automatically helps generated by the
ITS to the students in the processing of solving
specific problems. The hint developed following
to the degree of student motivation (Nesbit et al.,
2015).
The lack of ITS design in computer science is the
reusability of the same architecture in different ITS
contexts; each design applies to one objective (Crow
et al., 2018).
A Brief Review of using LMS in Computer Science Learning
199

3 CONCLUSIONS
This brief review reveals the different ways of
manipulating LMS to achieve learning for computer
science students. To point out that, researchers have
investigated extravagant efforts of improving distance
learning based on LMS by introducing intelligent
technics, to assure a high degree of apprenticeship,
even for: providing courses, feedbacks, hints,
according to the level of each student. That leads
to enhancing student learning engagement and tying
the stage of apprenticeship a new concept from one
student to another to balance the elevation of learning
inverse of students in the distance study.
Therefore, this research demonstrates each
technique’s weaknesses and effectiveness, which
will help us proposing our model to ensure adaptive
learning by using LMS to provide online education
for computer science learners for Moroccan students.
ACKNOWLEDGEMENTS
This work was supported by the Al-Khawarizmi
Program funding by Morocco’s Ministry of
Education, Ministry of Industry and the Digital
Development Agency (ADD) under Project No.
451/2020 (Smart Learning).
REFERENCES
Al-Khanjari, Z. and Al-Roshdi, Y. (2015). Developing
virtual lab to support the Computer Science Education
in Moodle. In Proceedings of 2015 12th International
Conference on Remote Engineering and Virtual
Instrumentation (REV), pages 186–191, Bangkok,
Thailand. IEEE.
Alharbi, A., Henskens, F., and Hannaford, M. (2011).
Computer science learning objects. In Proceeding
of the International Conference on e-Education,
Entertainment and e-Management, pages 326–328,
Bali, Indonesia. IEEE.
Alkhatlan, A. and Kalita, J. (2018). Intelligent Tutoring
Systems: A Comprehensive Historical Survey with
Recent Developments. arXiv:1812.09628 [cs]. arXiv:
1812.09628.
Almasri, A., Ahmed, A., Al-Masri, N., Sultan, Y. A.,
Mahmoud, A. Y., Zaqout, I., Akkila, A. N., and Abu-
Naser, S. S. (2019). Intelligent Tutoring Systems
Survey for the Period 2000- 2018. 3(5):17.
Almeida, T. O., de M. Netto, J. F., and Rios, M. L. (2017).
Remote robotics laboratory as support to teaching
programming. In 2017 IEEE Frontiers in Education
Conference (FIE), pages 1–6, Indianapolis, IN. IEEE.
Crow, T., Luxton-Reilly, A., and Wuensche, B. (2018).
Intelligent tutoring systems for programming
education: a systematic review. In Proceedings of the
20th Australasian Computing Education Conference
on - ACE ’18, pages 53–62, Brisbane, Queensland,
Australia. ACM Press.
Gunarathne, W. K. T. M., Shih, T. K., Chootong, C.,
Sommool, W., and Ochirbat, A. (2020). An
Automated Learning Content Classification Model
for Open Education Repositories: Case of MERLOT
II. Journal of Internet Technology, 21(5):1277–1288.
Number: 5.
Muhisn, Z., Ahmad, M., Omar, M., and Muhisn, S.
(2019). The Impact of Socialization on Collaborative
Learning Method in E-Learning Management
System (eLMS). International Journal of Emerging
Technologies in Learning (IJET), 14(20):137–
148. Publisher: International Journal of Emerging
Technology in Learning.
Nesbit, J., Liu, L., Liu, Q., and Adesope, O. (2015). Work
in Progress: Intelligent Tutoring Systems in Computer
Science and Software Engineering Education. In
2015 ASEE Annual Conference and Exposition
Proceedings, pages 26.1754.1–26.1754.12, Seattle,
Washington. ASEE Conferences.
Nwana, H. S. (1990). Intelligent tutoring systems: an
overview. Springer, page 27.
Patel, C., Gadhavi, M., and Patel, D. A. (2013). A survey
paper on e-learning based learning management
Systems (LMS). 4(6):8.
Riaz, S., Mushtaq, A., and Kaur, M. J. (2019). Intelligent
Tutoring for Informed Feedback in Interactive
Learning Environments. In 2019 Advances in
Science and Engineering Technology International
Conferences (ASET), pages 1–6, Dubai, United Arab
Emirates. IEEE.
Santos, G. S. and Jorge, J. (2013). Interoperable
Intelligent Tutoring Systems as Open Educational
Resources. IEEE Transactions on Learning
Technologies, 6(3):271–282.
Thamarai Selvi, S. and Panneerselvam, K. (2012). A
Self-regulated Learning approach for programming
language using cloud-based Learning Management
System. In 2012 International Conference on Recent
Trends in Information Technology, pages 191–196,
Chennai, Tamil Nadu, India. IEEE.
Wang, M., Wu, W., and Liang, Y. (2020). A
Novel Intelligent Tutoring System For Learning
Programming. In 2020 International Conference on
Development and Application Systems (DAS), pages
162–168, Suceava, Romania. IEEE.
Yulianto, B., Prabowo, H., Kosala, R., and Hapsara, M.
(2016). MOOC architecture model for computer
programming courses. In 2016 International
Conference on Information Management and
Technology (ICIMTech), pages 35–40, Bandung,
Indonesia. IEEE.
BML 2021 - INTERNATIONAL CONFERENCE ON BIG DATA, MODELLING AND MACHINE LEARNING (BML’21)
200