See discussions, stats, and author profiles for this publication at: https://www.researchgate.

net/publication/359970185

A Review Paper: The Implementation of Learner Model Approaches in the

Adaptive E-Learning Systems

Article in Journal of Applied Computer Science & Mathematics · April 2022

DOI: 10.4316/JACSM.202201001

CITATIONS READS

0 34

1 author:

Hiba A. Abu-Alsaad
Al-Mustansiriya University
14 PUBLICATIONS 16 CITATIONS

SEE PROFILE

Some of the authors of this publication are also working on these related projects:

Promotion requirements View project

All content following this page was uploaded by Hiba A. Abu-Alsaad on 19 April 2022.

The user has requested enhancement of the downloaded file.

 Journal of Applied Computer Science & Mathematics, Issue 1/2022, vol.17, No. 33, Suceava

A Review Paper: The Implementation of Learner Model Approaches in the

Adaptive E-Learning Systems

Hiba A. ABU-ALSAAD
Collage of Engineering, Mustansiriyah University, Baghdad, Iraq
[email protected]

Abstract – Recently, the systems of e-learning are improved An adaptive learning system based primarily on the use of the
technologically and the led to the emergence of e-learning systems individual information provided in the learner model for the
that reached the level of adaptation to students. Through which, purpose of designing instructional materials, such as exercises,
it changed the entire education system during the Internet era. quizzes, lessons, etc. and teaching methods for each student.
Nonetheless, the use of rule-based, assumption-based, and
network-based method have some vital methodologies used to
Based on this system (adaptive learning system), the e-learning
implement learner models across adaptive learning systems. The system only provides learning resources that are shared by all
so common way to structure the learner models approaches rely students [4]. The purpose of this paper is to present the
on the personalization and user modelling. However, previous methods of researchers' studies towards their
personalization and user modeling found out to be the best applications to learners' models through e-learning systems. In
approaches-not only in developing students' talents but also in addition, those methods such as framework/network-based,
allowing students to take their own learning direction and rule-based and assumption-based implementation standards
making sure that they are using their potential to the fullest. The are discussed in detail to help uncover some of the related
mismatching in viewpoints and perceptions between teachers and issues affecting the functions of adaptive learning systems.
technicians along with a lack of appropriate technical knowledge
have been identified as some of the major challenges affecting the
Also, approaches to implementing these learning systems such
learner model development. the main objective of this article is to as personalization and user modeling are analyzed with a keen
show the use of different approaches through the recent scholars’ interest in how these learning platforms can be improved. In
in implementing learner models within adaptive e-learning building a learner model, challenges and successes are
systems. Moreover, approaches and challenges in implementing investigated to help further improve this platform in all areas.
learner models are also described. The possible methods of implementing the learner model in
Keywords: Learner Model, Knowledge base, Dynamic Adaptive adaptive e-learning systems divided into;
Level Supposition based model, Adaptive E-learning system.
II. RULE-BASED METHOD
I. INTRODUCTION
Notably, in the rule-based methods, systems are viewed
In the educational of learning institutions system, the from certain aspects as a clear interpretation of the rules.
primary system of learning came out of those systems that Consistently, it is considered to be a representation based on a
would be oriented towards educating a large number of logical assumption as stereotypes for end users [5]. Therefore,
learners in a single concept. This model makes learners think it is viewed as a nested model as it connects and interacts with
and act the same way according to different situations related the region to which the model applies [6]. The recognition and
to the topic under discussion [1]. However, it was observed representation of different perceptions are usually dependent
that after conducting many researches that each student has on the ability of the system to accommodate these changes
individual traits that are completely different from other within the framework of its basic functions according to the
students and thus need to be addressed and improved in conviction and attitude of the user, various stereotypes as well
various ways that are unique to each student [2, 4, 5, 6, 7]. as user groups [7]. Basically, those groups can be dynamically
Students possess a various knowledge such as experiences, activated under certain conditions. In creating and opening
goals, ambitions, interests, knowledge, personality traits, adaptive systems within the controls of rule-based methods
learning backgrounds and activities, and outcome studies and adaptive as well as the interactive systems—the definition
which will be useful to build such systems [3]. Each learning of systems must be contained three distinct levels of consent
model is created to contain these needs, whereas, in the process [8, 9, 10, 11]. The first level is the standard experience in
of modeling learning, an “adaptive learning system” takes which the hierarchy and physical structure of learning content
advantage of learners' features to optimize the whole learning remains unchanged. The second level is a personal experience
structure while paying close attention to technological contains changes in the content hierarchy that will then adapt
developments that are seen to significantly affect the functions the user to different behavior and choices. The third level is
of such positional models [4]. the open experience where there is a direct and open system

DOI: 10.4316/JACSM.202201001 9
 Computer Science Section

coupled with continuous interaction between user, product, III. APPROACHES FOR IMPLEMENTING THE LEARNER MODEL
and the message.
A. Personalization and User Modelling
A. The Network or Framework-Based Method
One of the most successful approaches to implementing a
This method is naturally related to the discovery of sciences, learner model is to personalizing and adapt e-learning
the interactions and interrelationships between the discrete according to individual advantage, educational goals,
facts of the framework and semantic network [12]. Here the knowledge, and student preferences [27]. It is proven that this
role is to play in establishing facts according to the learner's approach not only attracts the attention of the learner, but also
specifications with keen interest in forming a knowledge base enhances their self-esteem in high performance on different
that suits their specifications and developing their expertise in fronts of the learning process [1]. It is necessary to understand
various disciplines [13]. The separation of facts will allow the the adaptability of the entire e-learning system to preferences
initiation of both the framework and the semantic framework, and to know the student's static, primary and dynamic levels.
which are important to clearly define learning structures in the The system in this pattern actually reviews the basic
an adaptive learning system [14]. In addition, it will allow the information of the student with close attention to the type of
interaction between the end-user and the system to be training enrolled, in addition goals and objectives as dictated
integrated so that each framework structure comes with its own by the initial information that it provides in the learning system
knowledge base establishes a specific learning area [15]. [28, 29]. Public personal information for all students is
Standardizing the information in the semantic network will extremely important at this system as it will be used to allocate
allow the interaction between the end-user and the system to learning resources to all students in a particular category by
fully evolve from each learning stage that is progressive from investigating general information about each student and
the previous learning styles [16]. categorizing them according to the general information within
B. Supposition-Based Methods the e-learning system [30]. For example, the system will be in
a position to classify all students enrolled from the initial
Through the Supposition-Based, method work with information students have provided to the system as required
different end-user assumptions which create a knowledge base from the initial date of the report [31]. Accordingly, the system
for students and rules that is independent of the domains [17]. will be in a position to separate these courses and group these
Those assumptions defined as those facts about the student that students in line with each major in all areas, such as students
the system will be taken within a certain level of argument and of accounting, biochemistry and political science etc. In this
information. For example, the reasoning system score then way, the initial distribution of knowledge and the learning
decreases if the student gives bad notes and rises if the student process can be easily implemented by adapting each student's
gives good feedback. Assumptions are best established knowledge base to his/her class [32].
through direct contact with the user (student). The scholars In the adaptive learning system, ‘personalization’ or ‘user-
selected this method as preference unit across the course modelling’ relies on two specific systems which are ‘static’
structure which will then be assigned by the adaptive learning and ‘dynamic’ adaptive systems. In the system of static
model [18, 19, 20]. Such structures, the student's interest and adaptive is set by selecting the most appropriate lesson from
the requirements of the learning process would dictate the the various activity lessons learned by the student as it is
entire context of the learning process—in addition a keen integrated into a specific personality within the stereotypical
interest in planning and rotating the entire educational material hierarchy [33]. Such as, by classifying according to the
[19]. In establishing such levels of assumptions, the end-user personality, students with relatively similar features are
knowledge requirements and reactions to the assimilation of presented an e-learning system together to highlight one area.
knowledge will determine the behavior that will be constructed Therefore, this personality classification takes into account not
the system. Accordingly, there are three different groups only the students' personalities but also the interests,
differentiated in the system assumptions, the first group is knowledge base, and preferences they tend to have while
what the student knows, the second group is what the students interacting with the adaptive system. The dynamic adaptive
does not know, while the third group addresses goals, plans, system was designed to guide the students' capabilities through
and tasks for the student [24, 25,26]. The primary two the curriculum. Such as, initially is to present instructions and
categories can be contextualized by the overlay and stereotype after, the students' knowledge and skills are estimated through
models as the knowledge of the students are being integrated the help of reactive activities [35]. In the dynamic adaptive
to the relevant domain ontology. The third category is an system, the student cannot move to next learning element
integral part of the tasks and objectives model for the adaptive sequentially before the entire result is carried out. Whereas,
e-learning system. Hence, linear parameters are considered as when all student answers are correct, setting the verification
an intelligible method—this method is more complicated but code will show the button of "next page”. The choice of the
more authoritative when it comes to usage, such as in terms of following learning element relies on the number of mistakes
wording, documents, Interval and temporal logic etc. the user made while solving the task they were assigned to
solve. Depending on the number of errors, the student is

10
 Journal of Applied Computer Science & Mathematics, Issue 1/2022, vol.17, No. 33, Suceava

redirected to an 'easy', 'medium', or 'more difficult' activity. A like scaling, enhancing usability, incorporating knowledge,
specific number of navigation algorithm errors identified and building based on realistic data.
individually for each activity via the author of the training
course. The report page is also dynamically generated at the IV. CONCLUSION
end of the sequence, depending on the specific path the user
took. Thus, the dynamic adaptive system created for the There is no doubt that e-learner models are on the rise in
system allows an understanding of the student's preferences recent years—technological advances and the need to
and a relevant lesson within the learning process with a keen empower humanity led to the emergence of adaptive e-
interest in exploring the student's abilities to assimilate learning systems that have changed the entire education
knowledge and talent in a specific field as it is integrated into system during the Internet era. Through the research, it is
different platforms of the knowledge base [35]. Then the concluded that the use of the rule-based method, the
relevant lesson replaces the current lesson which is more assumption-based method, and the network-based method
student-friendly. This system (the dynamic adaptive system) have some vital methodologies used to implement learner
not only views the student as the center of its own learning models across adaptive learning systems. In turn,
resource but also as the manager of the entire learning process personalization and user modeling are referred to as some of
with the goal of exploring the talents and student’s capabilities. the prominent approaches to implementing learner models.
Taking advantage of the talent gives the student an opportunity Personalization and user modeling have been found to be the
to do what interests him, so he tends to embrace every best approach not only in developing students' talents but also
challenge that comes with him [36]. The dynamic adaptive in allowing students to take their own learning direction and
system not only bends the rules for the talent to be portrayed making sure that they are using their potential to the fullest.
but also provides the student with a platform for sustainable
growth in knowledge empowerment and deep talent growth. ACKNOWLEDGEMENTS
An example of systems they used static learner model are in
The author would like to thank Mustansiriyah University
[43-47], However, author in [48] used both dynamic and static
(www.uomustansiriyah.edu.iq) Baghdad – Iraq for it is support
approaches in implementing their learner model.
in the present work.
B. Challenges in Build a Learner Model
V. REFERENCES
The impact of knowledge on the student in the modern
world of education requires different means and methods of [1]. Y. Eltigani, A. Mustafa, and S. M. Sharif, “An approach to
teaching. Many teachers usually do not possess the skills Adaptive E-Learning Hypermedia System based on Learning
necessary to successfully teach students in the current Styles (AEHS-LS): Implementation and evaluation,” Int. J.
knowledge-based economy. When devising with a suitable Libr. Inf. Sci., vol. 3, no. 1, pp. 15–28, 2011.
learner model, the only critical challenge is the lack of the [2]. V. Bradac and B. Walek, “A comprehensive adaptive system
necessary technological skills [37]. At some point, teachers for e-learning of foreign languages,” Expert Syst. Appl., vol. 90,
no. August, pp. 414–426, 2017, doi:
will want to embrace technology as a major component by
10.1016/j.eswa.2017.08.019.
creating profound structures for which e-learning systems can [3]. H. K. M. Al-Chalabi and A. M. Ali. Hussein, “Analysis &
be beneficial, but instead, a lack of appropriate knowledge and Implementation of Personalisation Parameters in the
technological knowledge will hold them back from achieving Development of Computer-Based Adaptive Learning
these acts [38]. Environment,” SAR J. - Sci. Res., vol. 3, no. 1, pp. 3–9, Mar.
IT professionals must work closely with teachers to come 2020, doi: 10.18421//SAR31-01.
up with a model that not only engages students but also creates [4]. H. AL-CHALABI and A. HUSSEIN, “Ontologies and
a suitable platform in working to improve the teaching Personalization Parameters in Adaptive E-learning Systems:
capabilities of teachers. Usually there is an inconsistency when Review,” J. Appl. Comput. Sci. Math., vol. 14, no. 1, pp. 14–
19, 2020, doi: 10.4316/JACSM.202001002.
coming up with the learner model, especially when education
[5]. Marengo, A. Pagano, and A. Barbone, “Data Mining Methods
professionals are not fully consulted, pose a challenge in the to Assess Student Behavior in Adaptive e-Learning Processes,”
whole process [39]. In addition, teaching professionals may in 2013 Fourth International Conference on e-Learning “Best
have differing views on model constructs that may not be fully Practices in Management, Design and Development of e-
in line with the mindset and way of thinking of the computer Courses: Standards of Excellence and Creativity,” 2013, pp.
technician responsible for preparing the e-learning model [40]. 303–309, doi: 10.1109/ECONF.2013.60.
There should also be consultation from several related [6]. M. Yarandi, H. Jahankhani, and A. H. Tawil, “An adaptive e-
educational bodies, the diverse opinions according to the learning Decision support system,” in 2012 15th International
different viewpoints of different professionals usually create a Conference on Interactive Collaborative Learning (ICL), 2012,
pp. 1–5, doi: 10.1109/ICL.2012.6402141.
particular challenge in documenting the entire e-learning
[7]. G. Zhao, Q. Zhang, J. Chu, Y. Li, S. Liu, and L. Lin,
system. Furthermore, there are few more challenges are “Augmented Reality Application for Plant Learning,” in 2018
addressed in adaptive systems including learner models in [41] IEEE 9th International Conference on Software Engineering

11
 Computer Science Section

and Service Science (ICSESS), 2018, pp. 1108–1111, doi: [22]. Vassileva, “Adaptive e-learning content design and delivery
10.1109/ICSESS.2018.8663953. based on learning styles and knowledge level *,” Serdica J.
[8]. P. Brusilovsky, S. Sosnovsky, and O. Shcherbinina, “User Comput., vol. 6, pp. 207–252, 2012.
Modeling in a Distributed E-Learning Architecture,” vol. 3538, [23]. S. Hammami and H. Mathkour, “Adaptive e-learning system
no. February 2016, L. Ardissono, P. Brna, and A. Mitrovic, Eds. based on agents and object petri nets (AELS-A/OPN),”
Berlin, Heidelberg: Springer Berlin Heidelberg, 2005, pp. 387– Comput. Appl. Eng. Educ., vol. 23, no. 2, pp. 170–190, Mar.
391. 2015, doi: 10.1002/cae.21587.
[9]. P. Brusilovsky, “KnowledgeTree: A distributed architecture for [24]. N. Radwan, “An Adaptive Learning Management System
adaptive e-learning,” in Proceedings of the 13th international Based on Learner’s Learning Style,” Int. Arab J. e-Technology,
World Wide Web conference on Alternate track papers & vol. 3, no. 4, pp. 228–234, 2014.
posters - WWW Alt. ’04, 2004, p. 104, doi: [25]. C. Serçe, F. N. Alpaslan, and L. C. Jain, “Adaptive Intelligent
10.1145/1013367.1013386. Learning System For Online Learning Environments,” in The
[10]. M. Yaghmaie and A. Bahreininejad, “A context-aware adaptive Handbook on Reasoning-Based Intelligent Systems, no.
learning system using agents,” Expert Syst. Appl., vol. 38, no. January, WORLD SCIENTIFIC, 2013, pp. 353–387.
4, pp. 3280–3286, Apr. 2011, doi: 10.1016/j.eswa.2010.08.113. [26]. Shanshan Wan and Zhendong Niu, “Adaptive Learning Objects
[11]. F. Essalmi, L. J. Ben Ayed, M. Jemni, Kinshuk, and S. Graf, “A Assembly with compound constraints,” in 2014 IEEE
fully personalization strategy of E-learning scenarios,” Comput. Computers, Communications and IT Applications Conference,
Human Behav., vol. 26, no. 4, pp. 581–591, 2010, doi: 2014, pp. 34–39.
10.1016/j.chb.2009.12.010. [27]. M. Ciolacu and R. Beer, “Adaptive user interface for higher
A. Paramythis and S. Loidl-Reisinger, “Adaptive Learning education based on web technology,” in 2016 IEEE 22nd
Environments and e-Learning Standards,” Second Eur. Conf. e- International Symposium for Design and Technology in
Learning, pp. 369–379, 2003, doi: 10.1.1.131.288. Electronic Packaging (SIITME), 2016, pp. 300–303.
[12]. H. Movafegh Ghadirli and M. Rastgarpour, “A model for an [28]. M. Holenko Dlab, I. Boticki, N. Hoic-Bozic, and C.-K. Looi,
intelligent and adaptive tutor based on web by Jackson’s “Adaptivity in Synchronous Mobile Collaborative Learning,”
Learning Styles Profiler and Expert Systems,” in Lecture Notes EDULEARN17 Proc., vol. 1, no. February 2018, pp. 454–460,
in Engineering and Computer Science, 2012. 2017, doi: 10.21125/edulearn.2017.1097.
[13]. U. C. Apoki, S. Ennouamani, H. K. M. Al-Chalabi, and G. C. [29]. W. Musumba, R. O. Oboko, and H. O. Nyongesa, “Agent-based
Crisan, “A Model of a Weighted Agent System for Personalised adaptive e-learning model for any learning management
E-Learning Curriculum,” in Modelling and Development of system,” Int. J. Mach. Learn. Appl., vol. 2, no. 1, May 2013,
Intelligent Systems, 2020, pp. 3–17. doi: 10.4102/ijmla.v2i1.6.
[14]. L. Mahnane, M. T. Laskri, and P. Trigano, “A Model of [30]. M. Tadlaoui, A. Chikh, and K. Bouamrane, “ALEM: A
Adaptive e-learning Hypermedia System based on Thinking Reference Model for Educational Adaptive Web Applications,”
and Learning Styles,” Int. J. Multimed. Ubiquitous Eng., vol. 8, in Intelligent and Adaptive Educational-Learning Systems:
no. 3, pp. 339–350, Aug. 2013, doi: 10.1021/la900628k. Achievements and Trends (Smart Innovation, Systems and
[15]. H. M. El-Bakry, A. A. Saleh, T. T. Asfour, and N. E. Technologies), 2013, pp. 25–48.
Mastorakis, “A new adaptive e-learning model based on [31]. S. Sfenrianto, Y. B. Hartarto, H. Akbar, M. Mukhtar, E. Efriadi,
learner’s styles,” in Proceedings of the 13th WSEAS and M. Wahyudi, “An adaptive learning system based on
international conference on Mathematical and computational knowledge level for English learning,” Int. J. Emerg. Technol.
methods in science and engineering, 2011, pp. 440–448. Learn., vol. 13, no. 12, pp. 191–200, 2018, doi:
[16]. P. Nedungadi and R. Raman, “A new approach to 10.3991/ijet.v13i12.8004.
personalization: integrating e-learning and m-learning,” Educ. [32]. P. Q. Dung and A. M. Florea, “An Architecture and a Domain
Technol. Res. Dev., vol. 60, no. 4, pp. 659–678, Aug. 2012, doi: Ontology for Personalized Multi-agent e-Learning Systems,” in
10.1007/s11423-012-9250-9. 2011 Third International Conference on Knowledge and
[17]. H. M. Ghadirli and M. Rastgarpour, “A Web-Based Adaptive Systems Engineering, 2011, pp. 181–185, doi:
and Intelligent Tutor by Expert Systems,” in Advances in 10.1109/KSE.2011.35.
Intelligent Systems and Computing, vol. 177 AISC, no. VOL. [33]. M. Hamada and M. Hassan, “An Enhanced Learning Style
2, 2013, pp. 87–95. Index: Implementation and Integration into an Intelligent and
[18]. Popescu, C. Badica, and L. Moraret, “Accommodating Adaptive e-Learning System,” EURASIA J. Math. Sci. Technol.
Learning Styles in an Adaptive Educational System.,” Inform., Educ., vol. 13, no. 8, pp. 4449–4470, Jul. 2017, doi:
vol. 34, pp. 451–462, 2010. 10.12973/eurasia.2017.00940a.
[19]. Alian and M. AL-Akhras, “AdaLearn,” in Proceedings of the [34]. Troussas, K. Chrysafiadi, and M. Virvou, “An intelligent
1st International Conference on Intelligent Semantic Web- adaptive fuzzy-based inference system for computer-assisted
Services and Applications - ISWSA ’10, 2010, no. April 2014, language learning,” Expert Syst. Appl., vol. 127, pp. 85–96,
pp. 1–7, doi: 10.1145/1874590.1874611. Aug. 2019, doi: 10.1016/j.eswa.2019.03.003.
[20]. Gutiérrez, V. Álvarez, M. Paule, J. Pérez-Pérez, and S. de [35]. M. Rani, R. Nayak, and O. P. Vyas, “An ontology-based
Freitas, “Adaptation in E-Learning Content Specifications with adaptive personalized e-learning system, assisted by software
Dynamic Sharable Objects,” Systems, vol. 4, no. 2, p. 24, Jun. agents on cloud storage,” Knowledge-Based Syst., vol. 90, no.
2016, doi: 10.3390/systems4020024. October, pp. 33–48, Dec. 2015, doi:
[21]. S. Marković, Z. Jovanović, N. Jovanović, A. Jevremović, and 10.1016/j.knosys.2015.10.002.
R. Popović, “Adaptive distance learning and testing system,” [36]. Garrido and E. Onaindia, “Assembling Learning Objects for
Comput. Appl. Eng. Educ., vol. 21, no. S1, pp. E2–E13, Aug. Personalized Learning: An AI Planning Perspective,” IEEE
2013, doi: 10.1002/cae.20510.

12
 Journal of Applied Computer Science & Mathematics, Issue 1/2022, vol.17, No. 33, Suceava

Intell. Syst., vol. 28, no. 2, pp. 64–73, Mar. 2013, doi: E-Learning Curriculum,” in Modelling and Development of
10.1109/MIS.2011.36. Intelligent Systems, 2020, pp. 3–17.
[37]. F. Essalmi, L. J. Ben Ayed, M. Jemni, Kinshuk, and S. Graf, [43]. H. AL-CHALABI and A. HUSSEIN, “Ontologies and
“Automating the E-learning Personalization,” in Human- Personalization Parameters in Adaptive E-learning Systems:
Computer Interaction and Knowledge Discovery in Complex, Review,” J. Appl. Comput. Sci. Math., vol. 14, no. 1, pp. 14–
Unstructured, Big Data, 2013, pp. 342–349. 19, 2020, doi: 10.4316/JACSM.202001002.
[38]. Chrysoulas and M. Fasli, “Building an Adaptive E-Learning [44]. H. K. M. Al-Chalabi and A. M. A. Hussein, “Ontology
System,” in Proceedings of the 9th International Conference on Applications in E-Learning Systems,” in 2020 12th
Computer Supported Education, 2017, no. April, pp. 375–382, International Conference on Electronics, Computers and
doi: 10.5220/0006326103750382. Artificial Intelligence (ECAI), 2020, pp. 1–6, doi:
[39]. N. Blazheska-Tabakovska, M. Ivanovic, A. Klasnja-Milicevic, 10.1109/ECAI50035.2020.9223135.
and J. Ivkovic, “Comparison of E-Learning Personalization [45]. [H. K. M. Al-Chalabi, “Evaluation of a Multi-Parameter E-
Systems: Protus and PLeMSys,” Int. J. Emerg. Technol. Learn., learning System using Web 3.0 Technologies,” in 2021 13th
vol. 12, no. 01, p. 57, Jan. 2017, doi: 10.3991/ijet.v12i01.6085. International Conference on Electronics, Computers and
[40]. A. Abu-Alsaad, "Agent Applications In E-Learning Systems Artificial Intelligence (ECAI), 2021, pp. 1–4, doi:
And Current Development And Challenges Of Adaptive E- 10.1109/ECAI52376.2021.9515191.
Learning Systems," 2019 11th International Conference on [46]. H. K. M. Al-Chalabi and A. M. Ali. Hussein, “Analysis &
Electronics, Computers and Artificial Intelligence (ECAI), Implementation of Personalisation Parameters in the
2019, pp. 1-6, doi: 10.1109/ECAI46879.2019.9042015. Development of Computer-Based Adaptive Learning
[41]. K. M. Al-Chalabi and U. C. Apoki, “A Semantic Approach to Environment,” SAR J. - Sci. Res., vol. 3, no. 1, pp. 3–9, Mar.
Multi-parameter Personalisation of E-Learning Systems,” in 2020, doi: 10.18421//SAR31-01.
Communications in Computer and Information Science, vol. [47]. U. C. Apoki, “The Design of WASPEC: A Fully Personalised
1341, no. February, Springer International Publishing, 2021, Moodle System Using Semantic Web Technologies,”
pp. 381–393. Computers, vol. 10, no. 5, p. 59, May 2021, doi:
[42]. U. C. Apoki, S. Ennouamani, H. K. M. Al-Chalabi, and G. C. 10.3390/computers10050059.
Crisan, “A Model of a Weighted Agent System for Personalised

Hiba A. Abu-Alsaad was born in Baghdad, Iraq, in 1983. She received the B.S. degree from the University of Mustansiriyah
of Iraq, Baghdad, in 2005 and the M.S. degree from the University of Politehnica (UPB), Bucharest, in 2016, both in Computer
& Software Engineering. She is working as a Lecturer at the Computer Engineering Department / Collage of Engineering,
Mustansiriyah University, Baghdad-Iraq.

13

View publication stats