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

net/publication/335845606

Adaptive eLearning System: Conceptual Framework for Personalized Study

Environment

Chapter · September 2019

DOI: 10.1007/978-981-15-0108-1_31

CITATIONS READS

6 2,306

2 authors:

Bhawna Dhupia Abdalla Alameen

Prince Sattam bin Abdulaziz University Prince Sattam bin Abdulaziz University
21 PUBLICATIONS 106 CITATIONS 36 PUBLICATIONS 240 CITATIONS

SEE PROFILE SEE PROFILE

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

The model approach of GLCM method of keyframe extraction and Kullback-Leibler distance similarity measure for Content based video retrieval system from video
databases View project

Online LAB Management System View project

All content following this page was uploaded by Bhawna Dhupia on 07 October 2019.

The user has requested enhancement of the downloaded file.

 Adaptive eLearning System:
Conceptual Framework for Personalized
Study Environment

Bhawna Dhupia(&) and Abdalla Alameen

Department of Computer Science, College of Arts and Science,

Prince Sattam bin Abdulaziz University,
Wadi Addwasir, Kingdom of Saudi Arabia
{b.dhupia,a.alameen}@psau.edu.sa

Abstract. e-Learning system provides web-based learners the facility to access

the courses online anytime anywhere through internet. Traditional e-Learning
system does not provide individualistic model for learner and is not suitable for
all types of learner opted for e-Learning course. Therefore, the satisfaction level
of the learner is not very high in maximum cases. This problem of individual
learning can be taken care by implementing Adaptive e-Learning. Adaptive
learning is more interactive and popular these days. This learning is the com-
bination of intelligent tutoring and machine learning. The delivery of the
learning material in Adaptive e-Learning is based on the knowledge, goal,
experience, interest and background of the learner. This paper gives a detailed
introduction to the concept adaptive e-learning environment and its components.
A student can choose the way of learning and according to that a suitable path is
assigned to them. This way of learning increase the interest of the learner and
positively influence the learning outcome of the course. Keeping this new
technique of e-learning, a framework for the implementation of adaptive system
is also proposed based on the basic principles of adaptive e-learning.

Keywords: e-Learning
Adaptive learning system
Conceptual framework

1 Introduction

The advancement of technology has affected the field of education extensively. Internet
as one of the advancements in technology has raised the standard of teaching through
numerous applications available online. Online learning is popularly known as e-
learning. E-learning is a web-based instruction through which learning material is
delivered to the learners. Many applications are available on the internet, but they only
provide HTML pages and are not concerned about the need or learning pattern of the
user. These learning materials are used by many users and can have different aims and
goals of learning. The material provided in eLearning was not able to solve the problem
of all the users due to the common syllabus and common learning styles. Therefore a
new e-learning system came into existence called Adaptive E-learning System, which
took care of various shortcomings in a traditional e-learning environment.

© Springer Nature Singapore Pte Ltd. 2019

A. K. Luhach et al. (Eds.): ICAICR 2019, CCIS 1075, pp. 334–342, 2019.
https://doi.org/10.1007/978-981-15-0108-1_31
 Adaptive eLearning System 335

Education is the field which is more affected by the advancement of technology.

Adaptive e-learning system (AES) has come to the fore in the last ten years. This e-
learning system is more effective and efficient web-based intelligent way of delivering
the education online. The AES is based on the user model, which gathers information
about the users, their goals of learning, learning pattern, knowledge level and their
aptitude. After gathering this information, it offers the best suitable style of learning to
the learners [19]. The AES is the combination of an intelligent system to adapt the
learning style of users and Web-Based Instruction (WBI), which is the combination of
audio, video, graphics, plain text and hyperlinks known as hypermedia to provide
relevant learning environment on the courses offered [1]. Adaptive learning is based on
the theory that identification of learning style is a very crucial tool to improve the
individual learning of a learner especially in online learning. In this system learner
expects to have a unique style of teaching that helps achieve the learning goal. Most
vital feature of adaptive learning is its ability to change the learning style and peda-
gogical environment for the learner depending on the continuous action of the user
during complete learning process. The change on the learning strategy is directly
related to the knowledge, goal, experience, interest and background of each and every
person [31].
Education enables a country to develop and achieve its goals of development and
prosperity. These days almost all the universities in the world are offering Hi-tech tools
such as Blackboard to impart the e-learning mode of education to educate the youth but
this need more to offer the personalized learning. Implementation of adaptive e-learning
system will prove to be more effective in achieving the set goals. A number of
applications are prevalent to support the adaptive e-learning pattern. To mention a few;
AES-CS [15], INSPIRE [14] and ILASH [16], are developed to implement the adaptive
e-learning system [5]. But the shortcoming of these is that most of the work is done on
the user’s level of knowledge and lacks many other features like learning styles which
have to be accompanied to implement the real adaptive e-learning system [6].
This paper reviews the earlier research done in the field of AES. The various
models offered to implement the adaptive learning environment; the framework of the
conceptual adaptive learning model is also discussed. It also explains components of
the adaptive learning environment.

2 Related Work

According to the Blooms Learning Taxonomy learning is improved when it is deliv-

ered in the learning style of individual [7]. The basis of adaptive learning lies in this
statement. The most crucial point is to implement the adaptive leaning system is to first
understand the learning style of each individual and then to formulate the teaching
strategy for each one of them separately. Cronbach mentioned that the results of the
learning are based on the characteristics of a person and their adaptability to learn the
things [8]. Bloom’s later findings state that one-to-one delivery of instruction is more
effective than a conventional group- teaching. Bloom believed that all students can
achieve high learning outcome provided the learning style is suitable to learner [9].
336 B. Dhupia and A. Alameen

Education has undergone a phenomenal change in the last decade. E-learning was
considered to be the best way to impart the training online and this system was adapted
by many educational institutions. But, as discussed in the introduction e-learning
cannot provide the customize education to the leaners. So, to overcome the short-
comings in e-learning, adaptive learning is being accepted by the educational organi-
zations. Many current researchers have conducted research on the benefits of delivering
education using adaptive e-learning system. According to Duong et al., implementation
of personalized learning system for Adaptive E-learning is formalized by knowing the
ontology of an individual. Ontology of a person helps to find out the character traits and
helps to design the personalized training pattern for them [10]. It also includes the user
personal profile and track of the user’s general searching and browsing behaviors. This
helps to decrease the burden of extra information which is not relevant to the learner
profile. By providing the learning pattern and material linked with the interest of the
learner provides greater confidence and satisfaction which results in achieving higher
learning outcomes [11].
Pashler et al. [17] have comments on learner styles that adapting the learner styles
gives better learning outcome. Learning styles are commonly defined as a group of
emotional, psychological and cognitive factors which collectively give an idea about
the learner characteristics, interaction and response to the learning environment offered
to them. Learning style also comprehends the information type, presentation style such
as visual, auditory or kinesthetic and learning actions. Sonwalkar recent study [12]
states that adaptive leaning model is highly contributed by artificial intelligence,
intelligent tutor, and adaptive control. The first step in adaptive learning implementa-
tion is to find out the behavior of a learner towards learning, then to conduct the
analysis of the learning behavior and finally to offer a learning model which suits to the
learning pattern of the learner. In order to understand the learning pedagogy of the
users, he suggested a learning cube will be discussed subsequently. Snow and Farr [27]
learning methodology is incomplete if the preference of the learner is not considered
while imparting the education. If the interest of the learner is not included during the
course delivery, the learning process is incomplete and unsuccessful. Russel [28] also
suggested that educator should identify the varied learning styles of the learner and
implement the respective style for imparting the education. According to a researcher
[32] the change of pattern during the learning process maintains enthusiasm to learn
among the learner. This method greatly affects the learning outcome of the learner.
Educator should also use latest technologies to make the learning process interesting
and interactive.

3 The Framework
3.1 Pedagogical Framework of Adaptive e-Learning System
The pedagogy of learning deals with the learning pattern of the learner based on their
knowledge, experience, situations, and environment. This also covers the learning
goals of every individual. As mentioned before, every learner has an own way of
learning. Following the pattern adapted provides the desired learning outcome. The
 Adaptive eLearning System 337

pedagogical framework is responsible for the representation of knowledge through

metadata [12]. The data is captured through a questionnaire which helps to rate the
knowledge and behavior of the learner. The data is analyzed by an intelligent system
and based on the formative evaluation a unique learning strategy is offered.

3.2 Conceptual Framework

Adaptation in learning model can be implemented in a better way by formulizing the
models required for adaptive e-learning system in an efficient manner. To define the
conceptual framework for the system, three models required need to be defined namely;
Domain Model, Learner Model and Adaptive Model. The domain model includes the
knowledge and information about the courses offered and learner model includes all the
information related to the learner and adaptive model deals with the techniques to offer
the learning patterns and many more material for the related course. These models will
be studied in the later course of the paper.
Domain Model: Domain model is a combination of both behavior and data. Domain
specific information shows the skills and status of the learner in specific subjects [31].
It can be called as a main conceptual model of any project. In the concept of an
adaptive environment, it contains information about the knowledge part of the course
contents to cooperate the application for the adaptive course delivery. It has all the
details of the course including topics, contents, modules, links, images, books which
design the structure of the information incorporated [20]. The main purpose of the
Domain Model is to classify the data based on some criteria fixed by the programmer.
The domain model perhaps contains information regarding student learning activities.
This model is capable of observing the activity of the learner and connects them to the
type of learning styles suitable for that particular learner. Adaptive learning material
includes text, graphics, audio, video, animation and simulations which are used to
design the suitable learning model for the learner [25]. There are two main components
of a Domain Model: course material and learning methods. Depending on the learning
style adapted by the learner, course material should support the learner. It should be in
accordance with the plan proposed by the system for the learner. The course material
and the learning method should be closely linked with each other to get the desired
result. It also focuses on the design of the audio-visual content and suitable links to
browse the course contents. The design should be user friendly for all the users and
browsing of information should also be easily accessed.
Learner Model: It contains all the information regarding the learner such as their
domain, level of knowledge, learning pattern and other personal information. It not
only saves the information but also tracks the learning records of the users [21, 30].
Information on learner model is divided into two major categories; domain-specific
information and domain-independent information [6]. Domain-specific information
tells everything related to the knowledge level, skills, understanding level, track records
learning behavior, evaluation records, etc. [29]. Domain-independent information may
include learning goals, which help to measure the performance of the learner to achieve
their goals. It may include cognitive capabilities such as thinking and reasoning skills
and team learning skill, motivational states that drive the learners, background, and
338 B. Dhupia and A. Alameen

experience, and preferences. According to Schiaffino et al., There are two methods for
managing the behavior of the user. First method is to track the repetitive behavior of the
learner during learning process. This tracking of behavior helps in designing a pref-
erence model for that individual learner [34]. The second approach is based on cog-
nitive behavior of the learner. This helps to understand the psychology of the learner
towards learning. This information helps to define the learning styles of the learner,
later can be assigned according to the analysis of the behavior [35].
Adaptive Model: This model is based on teaching-learning activities of the learner
[23]. The learning activities of the users are analyzed and according to their behavior,
they are categorized into various groups. According to one of the author, Sonwalker
[12, 13], the learners can be divided into five categories depending on their analysis,
namely; apprentices, incidental, inductive, deductive and discovery. Based on the
learning styles any one pattern can be offered to the learners. This model is responsible
for analyzing the behavior of the learner and to offer the learning techniques based on
the behavior. This model works by selecting the learning style according to the need of
the students and assigning the appropriate category for the learning process. These
categories are divided into different types of knowledge; such as basic knowledge,
procedural knowledge- to understand the concept in a systematic way, conceptual
knowledge- to link the topics by implementing it into a real example [4]. Utilizing this
information a complete learning module is assigned to the students until they reach the
end. They can have the capability or permission to reiterate the nodes for more clar-
ification and also for revision. The adaptive model also contains the link for the various
references which gives clarity about the concept that the learner is dealing with.
Adaptive model keep on reviewing the learning pattern of the student till the end. In
case, any change in the learning pattern is found, new learning style is offered to the
learner. According to the style, learning material, learning path, evaluation system is
also get changed.

4 Proposed Framework for Adaptive eLearning System

This section discusses the proposed framework to implement the adaptive e-learning
system. Adaptive e-learning system (AES) is an established area of research which is
an integrated technology with the concepts of CAI, ICT, and hypermedia [24]. Com-
puter Aided Information, Information and Communication Technology and Hyper-
media are combined to give an environment for adaptive learning. The adaptive
learning system has become very popular due to its ability to cater the needs of the
heterogeneous type of users. It is known that the learners don’t have the same level of
IQ levels. Hence it is useless to offer them the services which are perhaps above or
below their level. Adaptive learning offers the service according to the individual’s
profile. It helps learner to understand the concept according to their IQ level which
helps the student to understand the concept clearly and make the learning process
interesting for all categories of learners. As discussed above, there are three basic
models for adaptive learning environment namely; domain model, learner model, and
 Adaptive eLearning System 339

group model. Therefore, the framework of the adaptive learning revolves around this
basic structure.
The basic model of the AES framework is domain-model. This is primarily a source
for all types of data required for the system to carry forward. It includes all the
information relevant to the course offered in the system with all the details such as
syllabus, course content, quizzes, audio/video content, assignment, tests, etc. The most
important part of the model is Adaptive Engine. It is responsible for discovering
individual learning behavior of the learner. It will also track the preferences,
achievement and activities of the learning during whole learning process. According to
VanLehn and du Boulay [33], it works as a combination of loops, outer loop decides
which task should be offered to the learner and inner loop organize the steps to
complete the task assigned to the learner by outer loop. This process in the adaptive
engine is implemented with the help of learning algorithm. In our model also, it will be
working as a loop till the completion of the learning process. Behavior of the learner
will be tracked and changes if any found will be implemented in the preferred learning
style of the user.

Fig. 1. Adaptive e-Learning conceptual model

Figure 1 is a detailed conceptual framework for the project. The working of the
model is elaborated in five steps. At first step is for the user to enter the information
regarding the user profile which includes the personal information and the course which
a learner wants to adopt. After creating the profile, the user is prompted to fill a
questionnaire. This questionnaire consists of questions that enable to learn the learner’s
behavior. In the second step the data fed by the user will be segregated into student
information, learning, and course data. This information gathered in the third step will
be transferred to the predictive model of the system. Predictive model analyses the data
340 B. Dhupia and A. Alameen

gathered about the user preference for learning style. The questionnaire to learning
preference which is offered in the start of the registration the learner gets analyzed in
predictive phase. Based on the result, a learning pattern is offered to the learner. Later
this data gets transferred to the adaptive engine, where the course material and delivery
system will be assigned. During the learning process, the learning pattern gets analyzed
and if there is any change found in the learning style, the new pattern is assigned to the
same user. This change is implemented by intervention engine. There will be dash-
board available to each users and faculty member to track the progress of the course
conducted. As suggested by Sonwalker [11, 12], the learning pattern of the learner
keeps changing and needs to be tracked on regular basis. These learning patterns are
categorized by him into five categories, namely; Apprenticeship, Incidental, Inductive,
Deductive and Discovery. The change of learning style after analyzing the behavior of
learner during the course, helps the learner to increase the interest of the learner and
result in the effective outcome of the teaching [24]. Other researchers commenting on
the learning style mentioned that student learns in a better way if the teaching styles of
the students are adopted [26]. To know the preferred learning style of the student there
are few techniques to be followed such as a questionnaire or psychometric test. These
tests consist of questions related to the learner personality, behavior and attitude. By
analyzing these tests, domain system can be chosen as to which learning styles can be
adopted for a specific learner Depending on the result, preferred style can be visual,
auditory and kinesthetic [21]. The learner model dynamically records the learning
aspects of the user such as preferences, interest and knowledge level. The more
accurate the analysis of the data related to the leaner, the better will be the solution or
the method of teaching provided. Further, they can be grouped into various categories
of learners depending upon the criteria like knowledge level, cognitive skills, learning
styles, motivation, age, gender, goal and learning objective.

5 Conclusion and Future Work

Adaptive Learning is an enhancement on the traditional e-learning system to make e-

learning more interactive and user centric. The main purpose of this paper is to study
about the adaptive e-learning system, benefits and proposal of a conceptual model
based on basic principle of adaptive learning. This paper covers the detailed intro-
duction of the adaptive e-learning system along with its components. Depending upon
the principles a conceptual model is also proposed. Universities are investing lots of
capital in implementing e-learning system. So, this has become very crucial to evaluate
the utilization of the LMS being implemented in the system. No doubt, BB is a well-
known and efficient LMS but whether it has been exploited in its fullest or not which
matters the most. Next step for the research is to evaluate the usage of the existing
system. This will be done by taking survey from the users of the e-learning system.
There are many open LMS are available in the market. In future work, a review of open
LMS will also be done and most suitable will be chosen for the implementation based
on proposed conceptual model.
 Adaptive eLearning System 341

Acknowledgement. This project was supported by the deanship of scientific research at Prince
Sattam bin Abdulaziz, University Kingdom of Saudi Arabia under the research project #
2017/01/7978.

References
1. Khan, B.H.: Web-based instruction (WBI): what is it and why is it? In: Khan, B.H. (ed.)
Web-Based Instruction, pp. 5–18. Educational Technology Publications, Englewood Cliffs
(1997)
2. Brusilovsky, P.: Developing adaptive educational hypermedia systems: from design models
to authoring tools. In: Murray, T., Blessing, S., Ainsworth, S. (eds.) Authoring Tools for
Advanced Technology Learning Environments: Toward Cost-Effective Adaptive, Interac-
tive, and Intelligent Educational Software. Ablex, Norwood (2002)
3. Lee, J., Park, O.: Adaptive instructional systems. In: Spector, J.M., Merrill, M.D., van
Merrienboer, J., Driscoll, M.P. (eds.), Handbook of Research on Educational Communi-
cations and Technology, 3rd edn., pp. 469–484. Taylor Francis, New York (2008)
4. Fouad, K.M., Nagdy, N.M., Harb, H.M.: Adaptive E-learning system based on semantic
search and recommendation in the Arab World. In: Information Systems Applications in the
Arab Education Sector, pp. 254–283. IGI Global (2013)
5. Drissi, S., Amirat, A.: An adaptive E-learning system based on student’s learning styles: an
empirical study. Int. J. Distance Educ. Technol. (IJDET) 14(3), 34–51 (2016)
6. Stash, N., De Bra, P.: Incorporating cognitive styles in AHA! (The Adaptive Hypermedia
Architecture). In: Proceedings of the International 28 International Journal of Library and
Information Science Conference Web-Based Education (IASTED), Innsbruck, Austria,
pp. 378–383 (2004)
7. Bloom, B.S.: Mastery Learning: Theory and Practice, pp. 47–63. Holt, New York (1971)
8. Cronbach, L.J.: The two disciplines of scientific psychology. Am. Psychol. 12(11), 671
(1957)
9. Bloom, B.S.: The 2 sigma problem: the search for methods of group instruction as effective
as one-to-onetutoring. Educ. Res. 13(6), 4–16 (1984)
10. Duong, T.H., Uddin, M.N., Li, D., Jo, G.S.: A collaborative ontology-based user profiles
system. In: Nguyen, N.T., Kowalczyk, R., Chen, S.-M. (eds.) ICCCI 2009. LNCS (LNAI),
vol. 5796, pp. 540–552. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-
04441-0_47
11. Akbulut, Y., Cardak, C.S.: Adaptive educational hypermedia accommodating learning
styles: a content analysis of publications from 2000 to 2011. Comput. Educ. 58(2), 835–842
(2012)
12. Sonwalkar, N.: The first adaptive MOOC: a case study on pedagogy framework and scalable
cloud architecture—Part I. In: MOOCs Forum, vol. 1, no. P, pp. 22–29. Mary Ann Liebert,
Inc., USA (2013)
13. Sonwalkar, N.: Adaptive individualization: the next generation of online education. Horizon
16(1), 44–47 (2008)
14. Papanikolaou, K.A., Grigoriadou, M., Kornilakis, H., Magoulas, G.D.: Personalising the
interaction in a web-based educational hypermedia system: the case of INSPIRE. User
Model. User-Adap. Inter. 13(3), 213–267 (2003). https://doi.org/10.1023/A:1024746731130
15. Trantafillou, E., Pomportsis, A., Georgiadou, E.: AES-CS: adaptive educational system
based on cognitive styles. In: Proceedings of the Workshop on Adaptive Systems for Web-
based Education, Held in Conjunction with AH 2002, Malaga, Spain (2002)
342 B. Dhupia and A. Alameen

16. Bajraktarevic, N., Hall, W., Fullick, P.: ILASH: incorporating learning strategies in
hypermedia. In: Proceedings of the Fourteenth Conference on Hypertext and Hypermedia,
Nottingham, UK, 26–30 August 2003
17. Pashler, H., McDaniel, M., Rohrer, D., Bjork, R.: Learning styles: concepts and evidence.
Psychol. Sci. Public Interest 9, 105–119 (2008)
18. Brown, J.D.: Testing in language programs: a comprehensive guide to English language
assessment (New edition) (2005)
19. Esichaikul, V., Lamnoi, S., Bechter, C.: Student modelling in adaptive e-learning systems
20. Paramythis, A., Loidl-Reisinger, S.: Adaptive learning environments and eLearning
standards (2004)
21. Nguyen, L., Do, P.: Learner model in adaptive learning (2008)
22. Kim, K., Choi, Y.-J., Kim, M., Lee, J.-W., Park, D.-S., Moon, N.: Teaching-learning activity
modeling based on data analysis. Symmetry 7(1), 206–219 (2015)
23. Saberi, N., Montazer, G.A.: A new approach for learners’ modeling in e-learning
environment using LMS logs analysis. In: 2012 Third International Conference on E-
Learning and E-Teaching (ICELET), pp. 25–33. IEEE (2012)
24. da Silva, D.P., Durm, R.V., Duval, E., Olivié, H.: Concepts and documents for adaptive
educational hypermedia: a model and a prototype. In: Presented at the 2nd Workshop on
Adaptive Hypertext and Hypermedia HYPERTEXT 1998, Pittsburgh, 20–24 June 1998
25. Cannataro, M., Cuzzocrea, A., Mastroianni, C., Ortale, R., Pugliese, A.: Modeling adaptive
hypermedia with an object-oriented approach and XML. In: Presented at the 2nd
International Workshop on Web Dynamics (WebDyn 2002) in Conjunction with the 11th
International World Wide Web Conference (WWW 2002), Honolulu, Hawaii (2002)
26. Rasmussen, K.L., Davidson-Shivers, G.V.: Hypermedia and learning styles: can perfor-
mance be influenced? J. Educ. Multimedia Hypermedia 7(4), 291–308 (1998)
27. Snow, R., Farr, M.: Cognitive-conative-affective processes in aptitude, learning, and
instruction: an introduction. Conative Affect. Process Anal. 3, 1–10 (1987)
28. Tseng, J.C.R., Chu, H.-C., Hwang, G.-J., Tsai, C.-C.: Development of an adaptive learning
system with two sources of personalization information. Comput. Educ. 51(2), 776–786
(2008)
29. Honey, P., Mumford, A.: The Manual of Learning Styles. McGraw-Hill, Maidenhead (1982)
30. Dung, P.Q., Florea, A.M.: An approach for detecting learning styles in learning management
systems based on learners’ behaviours. In: International Conference on Education and
Management Innovation, vol. 30, pp. 171–177 (2012)
31. Froschl, C.: User modeling and user profiling in adaptive e-learning systems. Master thesis,
Graz, Austria (2005)
32. Becker, S.A., Cummins, M., Davis, A., Freeman, A., Hall, C.G., Ananthanarayanan, V.:
NMC horizon report: 2017 higher education edition (2017)
33. Vanlehn, K.: The behavior of tutoring systems. Int. J. Artif. Intell. Educ. 16(3), 227–265
(2006)
34. Schiaffino, S., Amandi, A.: Intelligent user profiling. In: Bramer, M. (ed.) Artificial
Intelligence An International Perspective. LNCS (LNAI), vol. 5640, pp. 193–216. Springer,
Heidelberg (2009). https://doi.org/10.1007/978-3-642-03226-4_11
35. Gena, C., Weibelzahl, S.: Usability engineering for the adaptive web. In: Brusilovsky, P.,
Kobsa, A., Nejdl, W. (eds.) The Adaptive Web. LNCS, vol. 4321, pp. 720–762. Springer,
Heidelberg (2007). https://doi.org/10.1007/978-3-540-72079-9_24

View publication stats