ArticlePDF Available

Abstract and Figures

p class="Abstract"> A directed graph represents an accurate picture of course descriptions for online courses through computer-based implementation of various educational systems. E-learning and m-learning systems are modeled as a weighted, directed graph where each node represents a course unit. The Learning Path Graph (LPG) represents and describes the structure of domain knowledge, including the learning goals, and all other available learning paths. In this paper, we propose a system prototype that implements a propose adaptive learning path algorithms that uses the student’s information from their profile and their learning style in order to improve the students’ learning performances through an m-learning system that provides a suitable course content sequence in a personalized manner. </p
Content may be subject to copyright.
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Automated Adaptive Mobile Learning System using
Shortest Path Algorithm and Learning Style
Ibrahim Alkore Alshalabi!!"
Al-Hussein Bin Talal University, Jordan.
Samir E. Hamada
Farmingdale State College, Farmingdale NY, USA
Khaled Elleithy, Ioana Badara
University of Bridgeport, Bridgeport CT, USA
Saeid Moslehpour
University of Hartford, Hartford CT, USA
AbstractA directed graph represents an accurate picture of course de-
scriptions for online courses through computer-based implementation of various
educational systems. E-learning and m-learning systems are modeled as a
weighted, directed graph where each node represents a course unit. The Learn-
ing Path Graph (LPG) represents and describes the structure of domain
knowledge, including the learning goals, and all other available learning paths.
In this paper, we propose a system prototype that implements a propose adap-
tive learning path algorithms that uses the student’s information from their pro-
file and their learning style in order to improve the students’ learning perfor-
mances through an m-learning system that provides a suitable course content
sequence in a personalized manner.
KeywordsAdaptive Learning, m-learning, Learning style, Shortest Path, Al-
1 Introduction
E-LEARNING researchers explore and develop adaptive techniques that provide a
better educational experience for students. Researchers offer accurate and personal-
ized content to students in an intelligent way [1], that may allow for adjustments in
course content based on students most recent performances. This technique allows the
student to skip unnecessary learning activities by providing automated and personal-
ized support for the student [2]. Students with different educational backgrounds are
the main challenge of the e-learning and m-learning systems. These systems provide
personalized course units that meet different students’ educational needs.
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
2 Related Work
Adaptive learning makes the learning process easier, faster, and more effective by
personalizing the course content for the students based on students’ profile. Since
adaptive learning systems are still being developed, many issues about adaptive learn-
ing have concerned computer science and education researchers. Many techniques
and approaches are being introduced. Eventually, these techniques will greatly im-
prove the future of adaptive learning systems. They will adjust more rapidly to the
students’ goals and preferences. Many different techniques were proposed to generate
the adaptive learning paths. These approaches are categorized based on the techniques
used to generate an effective learning path.
The current challenge in designing adaptive systems is to provide personalized
courses to different students with different learning strategies that are practical to use
and more efficient [3][4]. Based on the variety of adaptive learning techniques, they
posses’ different capabilities in manipulating the learning systems, however, none of
these techniques are suitable for all tasks and situations. The Learning Path Graph
Technique represents and describes the structure of domain knowledge, the learning
goals, and all available learning paths [5][6]. Based on the student’s learning paths
and learning goals, the student’s attributes such as the level of knowledge, the learn-
ing style and preferences are used to select a personalized learning path from the
Learning Path Graph.
The Concept Map Technique represents the entire course structure and the
knowledge of the course domain. The role of Ontology is to describe the learning
materials that are composed together in order to create a course [7][8][9]. The Ex-
tended Ant Colony Technique combines the previous user’s learning profile and an
ant colony system approach in order to generate an adaptive learning path [10]. The
Ant Colony Optimization (ACO) Technique predicts the best path based on the stu-
dent’s profile and the previous learning paths that have been followed by previous
The students are grouped by using the clustering technique based on their learning
styles. The technique using Bayesian networks to generate an adaptive learning path
is based on learning styles, level of expertise, etc. Based on Bayesian Probability
Theory, a node probability table is created. This table has the node probability based
on candidate learning paths that consist of different consequent nodes and could be
traversed from the current node. Then, the Bayesian network is constructed to calcu-
late the probability value which represents each knowledge unit in the learning path.
To create candidate learning paths, the shortest path is selected to provide the appro-
priate learning path for students [11].
Based on the above referenced works, it is evident that further research is neces-
sary to improve the efficiency of learning systems. Accordingly, our research focuses
on discovering the effective learning path. In addition, we need to emphasize on addi-
tional adaptation features, smart techniques that can be used to identify the learning
style, different educational experiences, skills, learning and learning preferences
based on student’s interactions and different types of learning mode that lead to better
learning abilities.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
3 Methodology
A directed graph represents an accurate picture of course descriptions for online
courses through computer-based implementation of various educational systems [12].
E-learning and m-learning systems are modeled as a weighted directed graph where
each node represents a course unit [13]. The Learning Path Graph (LPG) represents
and describes the structure of domain knowledge, including the learning goals, and all
other available learning paths. This paper proposes adaptive learning path algorithms
that use the student’s information from their profile in order to improve students’
learning performance through e-learning and m-learning systems that provide suitable
course content sequence in a dynamic form for each learner.
3.1 Learning Path Graph (LPG)
In general, the LPG illustrates the structure of domain knowledge and the learning
goals and all available learning paths [14] [15].
In order to create and generate a Domain Concept Module (DCM), a two-step pro-
cedure is implemented [15].
The first part consists of a designing Learning Goals Hierarchy (LGH) and Con-
cepts Hierarchy (CH) of the Domain Concept Module. Concepts Path Graph (CPG) is
a directed acyclic graph which represents the structure of the Domain Concept Mod-
ule (DCM) which is generated from the connection between the Learning Goals Hier-
archy (LGH) and the Domain Concept (DC). The learning path graph is a directed
acyclic graph which represents all possible learning paths that match the targeted
learning goal. In order to build the Learning Path Graph (LPG), within each concept
of the Concept Path Graph (CPG), associated learning resources are selected from
media space database. Media space database describes the educational characteristics
of the learning resources.
The second part of Domain Concept Module (DCM) includes a personalized learn-
ing path. A personalized learning path is selected from the graph that contains all the
available learning paths according to the characteristics of the Student Module (SM).
The Student Module (SM) identifies a level of student expertise (student knowledge
space), learning style (cognitive characteristics) and preferences. The suitability func-
tion is applied in order to find the weight of each connection of the Learning Path
Graph (LPG) to provide a suitability factor for learning resources.
By applying the adaptive shortest path algorithms to the weighted graph, the sys-
tem will generate the optimal learning path for a specific student.
3.2 Student Profile
The main challenge of the e-learning and m-learning systems is to create an appro-
priate adaptive course sequence to provide different students with different education-
al backgrounds. One of the most important aspects of these systems which has not
been completely thoroughly examined, is the capability of the learning system to
adapt to the students’ profile [16]. An adaptive learning path algorithm uses the stu-
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
dent’s information from their profile to improve the e-learning and m-learning sys-
tems and to provide suitable course content sequence in a dynamic form for each
student [17].
3.3 Using graphs to represents course units
Graphs are considered as an efficient representation of online courses where have
been used in the implementation of e-learning and m-learning systems. The course
content is divided into portions called learning atoms that could be implemented at all
levels and learning modes [18]. Each course unit could be represented as a graph that
includes the learning objectives located on the nodes and after the partition of the
nodes. The graph will contain course concepts (Slide, Text, Examples, and Video etc.)
4 Adaptive Shortest Path Algorithm
Most of the styles are intuitive. However, we invite the reader to read carefully the
brief description below.
4.1 Document title and meta-data
Fig. 1, below, represents course units that consist of n units whereas G is a graph
with n vertices where n >= 0. Let V(G) = { v1, v2,…..,vn }. W is a two dimensional n
x n matrix such as:
!!"!!!" !!!!!
!!"!!"!!"#!!!"!!!!"# !!!!!!!!!!
!!" !"!!!!!!"#$!!!!"!!!!!!"#! !!!!
!!!"!!!!"!!!"!!" !!"#!!!"#$!!!!!!"!!
Fig. 1. Weighted graph represents the course units (CUs) structure.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
The adaptive shortest path consists of two stages: In stage 1 the algorithm-1 identi-
fies the minimum cost matrix between each pair of course/learning units (CUs). In
stage 2 the algorithm-2 constructs an optimal learning path for each student. The
shortest learning path designs an adaptive environment for individual students based
on the minimum cost between each pair of course learning units and their relevant
personal information.
In stage 1, in order to locate the minimum cost matrix between each pair of
course/learning units, we applied algorithm-1. Algorithm-1 was implemented through
the following steps:
Step 1: Input matrix W which represents the weighted graph course units’ struc-
Step 2: For X=1 to X<N repeat step3tostep 7where N is equal to number of CUs;
Step 3: For I= 1 and I<= N repeat step 4;
Step 4: For J= 2 and J<= N repeat step 5, step 6 and step 7;
Step 5: Compare If WIJ > (WIX + WXJ), if true then [19]
Compare If PIX=0, if true then
Step 6: Compare If WIJ < (WIX + WXJ). if true then
No change;
Step 7: Compare If WIJ = (WIX + WXJ), if true then
Compare If PIX=0 if true then
PIJ = X+1;
Create new PcmID+1 (I, J) =CU (Alternative path for IJ);
Create new W+1 (I, J) =CU (Alternative minimum cost for IJ) where
New WIJ +1= WIJ;
Step 8: End.
We assumed that there is no path between the same node, so for each I=J then WIJ
= ! and where each WIJ=! then PIJ=! was modified.
In stage 2; in order to identify the shortest path movement between each pair of
course/learning units we, applied Algorithm-2.
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Algorithm-2. Algorithm-2 represents the shortest path movement between CUI
and CUJ. We followed the steps listed below:
Step 1: CUI start node and CUJ end node (Target node);
Step 2: if PIJ= ! then no path between CUI and CUJ go to Step 7;
Step 3: If PIJ= 0, if true then
PIJ is end node (Target node in shortest path);
Go to Step 7;
Step 4: Repeat Step 5, Step 6 and Step 3;
Step 5: PIJ is next node in shortest path;
Step 6: I=PIJ;
Step 7: End.
5 Mathematical View
To explain how algorithms work, First, we created an initial weighted matrix
W=W, where WIJ is the arrowhead weight from CUI to CUJ. Then, we initialized the
weighted matrix W from graph in Fig. 1 as shown in Table 1 as follow:
If no arrowhead exists between the two CUs, then the WIJ = !.
For each I=J, then WIJ = !.
Table 1. Graph from Fig. 1 Represented by W(N,N) Matrix, Where N is the number of Course
Units= 5.
4 10
Then, we created Table 2, where P is path matrix: P is a two dimensional n x n ma-
trix such that for each P(I, J) = { p11 = p12 = p13 …. pnn = 0}:
Table 2. Initialized Shortest Path Traveling Matrix by 0 Between Any CUs: P (I, J)=0.
P(5,5) CU-1 CU-2 CU-3 CU-4 CU-5
After applying Algorithm 1, in stage 1, we generated Table 3 and Table 4:
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Table 3. Shortest Path Traveling Cost Matrix W (I, J) between any CUs
W(5, 5)
Table 4. Shortest Path Traveling Matrix P(I, J) for CUs
After applying to each I=J for cost matrix, then W(I,J )= ! as shown in Table 5:
Table 5. W(I,J ) is the Shortest Path Traveling Cost, for Each I=j Cost Matrix W(I,J)= !.
12 7
After applying to each, W(I,J )=! then P(I,J )=! as shown in Table 6:
Table 6. Shortest Path Traveling Matrix P for Each W(I, J) =!, Then P(I,J )=!.
0 0 3 2
0 3 0
In stage 2, Algorithm-2 was applied in order to find the shortest path movement be-
tween the learning CUs according to the results shown in Table 6.
Now we need to find the shortest path cost CU1"CU5. The solution is reflected in
Table 5 where W(1,5)=14. And then, determine the path movement between CU1 and
CU5. In order to complete this task, we use Table 6 to locate the path movement be-
tween CU1 and CU5 as follows:
From Table 6 the path beginning with CU1"CU5=2, then CU2"CU5=0 (end
nod), then the path is CU1"CU2"CU5
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
6 Adaptation of the Shortest Path Algorithm to the Relevant
Personal Student Information
In our first scenario, assume the student is at the initial stage and logs into the sys-
tem, the student begins the coursework with the CU1. After student successfully fin-
ishes and wants to continue onto CU2, the system will direct the student towards the
shortest path CU1"CU2 which is equal to 8.
In second scenario, assume the student has completed the coursework in CU1 and
CU2 and has logged out of the system. The student, then, decides to log back into the
system to complete CU3, the system automatically direct the student from
CU1"CU3 which is equal to 7. The system does not take CU2 into consideration and
ultimately affect the student learning path based on student’s personal information.
To make the Algorithm3.2 more adaptive to student’s profile the flow of Algo-
rithm3.2 must be accordingly:
Once the student completes a new CU, the system will update the student’s per-
sonal profile with the new information. Therefore, if the student decides to learn the
new a CU, the system will identify the shortest path between each CU in the student’s
profile as well as any new CUs that the student plans to study.
A. Algorithm-3
Step 1: For each CU learned in the student’s profile complete Step 2;
Step 2: Find the shortest path between CUs in the student’s profile and new target
CU by using the result from Table 5;
Step 3: Find the minimum cost from all of the shortest paths to the new target CU
between CUs in the student’s profile and the new CU target;
Step 4: Then determine the shortest path according to the student’s profile that re-
flect the Cui (min cost) to the new target CU;
Step 5: Use Algorithm 2 and Table 6 to find the shortest path movement between
learning CUi (min cost) and new target CU;
Step 6: If student complete the newly targeted CU, then the student’s personal pro-
file will automatically be updated by the system;
Step 7: End.
Once Algorithm-2 has been modified, then in following scenario assumes the stu-
dent is at the initial stage and logs into the system, the student completes CU1. After
once CU1 is completed, the student moves onto CU2 and the system will direct the
student to the shortest path CU1"CU2 which is equal to 8. This information is stored
in the student’s profile.
However, the next time the student logs onto the system to study CU3, by applying
Algorithm 3 according to the student’s profile, the system will compare
CU1"CU3=7 with CU2"CU3=4 and then, the system will direct the student to the
path CU2"CU3 which is equal to 4.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
The personalization of a student’s learning path is the core feature of the e-learning
and m-learning systems processes. Our current algorithms will construct an adaptive
m-learning prototype for Computer Science courses.
7 Automatic Detection of Learning Style
Fig. 2. AML System Contents According to Learning Style
Our AML learning system presents course instruction for students by using the
shortest path algorithm in order to find the most efficient learning path between the
learning course units (CUs), according to students’ profiles. In order to discover the
most effective path, we need to implement and use learning style methods in the de-
signing stage of course content.
According to a student’s learning style, we can introduce the same course content
through different presentation methods as shown in Fig 2. In our AML system design,
we used the Data Driven Method based on the Index of learning style questionnaires
created by Felder and Soloman [20]. In addition, we used the Literature Based Meth-
od [21] that uses the students’ behavior in order to determine a student’s learning
style. Both the Data Driven Method and the Literature Based Method were used as
base tools for analyzing students’ learning styles.
The Index of Learning Styles is used for identifying learning style preferences in
the Felder and Soloman model. The Index of Learning Styles has 44 questions. The
Felder and Soloman model has four dimensions where each dimension defines two
differing learning styles. Each dimension has 11 questions containing two options).
Also, each dimension uses scaling values between -11 to +11.
The student’s results indicate which learning style the student like better, for ex-
ample if a student’s scaling result is between -3 to +3, then the student prefer the two
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
learning styles of the dimension equally. Otherwise, the student prefers one learning
style more than the other of the dimension [22].
The reason for the Index of Learning Style questionnaire is that it provides us with
important information to determine the type of content necessary for the students
according to their learning styles. The Index of Learning Style questionnaire can be
easily implemented to analyze the students’ learning styles [23].
According to the model introduced by Felder and Soloman and [24] [25] [26], the
learning contents in our AML system are categorized as shown in Table 7.
Table 7. Four Dimensions of Learning Style
Our AML system can select appropriate learning styles with attention to the behav-
ior and appropriate needs of the student. The AML system adapts to the student’s
learning style by implementing a learning style assessment and the Literature Based
Method. Both were used in our AML system to identify the student’s learning style.
According to the Student Learning Style Module, this process can be completed in
the following ways:
a) Initial Learning Style Adaptation: If the student decides not to take the learning
style assessment based on the Felder and Soloman Index of Learning Styles, by
default, the students learning styles are categorized as active, sensing, sequential,
and visual. The AML system will provide students with the appropriate learning
content according to the Initial Learning Style [27] [28].
b) Student Learning Style Adaptation: At the beginning of the course, the AML sys-
tem provides the student with the learning style assessment. If the student decides
to take the learning style assessment, then the AML system will analyze the learn-
ing style assessment results and provide students with the right learning content
according to the student’s learning style [29].
c) Literature Based Method Adaptation: The Literature Based Method is used in our
AML system to automatically identify students learning styles based on the fea-
tures of Learning Style Module that describe students’ behaviors. The features
and the behavior patterns in our Learning Style Module refer to the Felder and
Soloman model that have been used in our system’s design. In our system, we
adapt the following behavior patterns:
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
1) Active Learning Style: Can be identified by the number of exercises that a stu-
dent completed, the number of questions that a student answered, and the
number of questions that a student fails to answer twice or more.
2) Reflective Learning Style: Can be identified by the number of reviewed learn-
ing materials, and the time spent on this learning material.
3) Sensing Learning Style: Can be identified by the number of correct answers
about facts, the number of correct answers after reviewing the examples, and
the number of correct answers after seeing practical material.
4) Intuitive Learning Style: Can be identified by the number of correct answers
given after a theoretical explanation, the number of correctly answers about
concepts, the number of correct answers about creating new solutions.
5) Visual Learning Style: Can be identified by the number of correct answers giv-
en after seeing graphs, charts, images and video, and time spent watching vid-
6) Verbal Learning Style: Can be identified by the number of correct answers
given after reading text, and the number of correct answers given after listen-
ing to audio.
7) Sequential Learning Style: Can be identified by the number of times the stu-
dent prefers to the step by step problem solving, and the number of correct an-
swers about details.
8) Global Learning Style: Can be identified by the number of times the student
decides to solve a problem directly, the number of reviewed outlines, and the
time spent on outlines.
According to [30], the behavior patterns as described above and the students’ in-
formation based on these behaviors are used to obtain the hints in order to calculate
the student’s learning style. Hints are described as (hdim, i), where hints are collected
for every dimension (dim) and every pattern(i) that includes related information for
this dimension.
After we determine the relevant features (patterns) of students’ behavior, based on
Felder and Soloman learning style model, we need to use a threshold value to classify
the occurrence of behavioral patterns. The threshold value identifies the presence of
behavioral patterns and categorized them based on the hint of 0 to 3, where, 0 = no
information about students’ learning style, 1 = low (e.g., reflective), 2 = moderate
does not provide a specific hint, and 3 = high (e.g., active). To find the student’s
learning style, we apply the following [30]:
1. Sum up all hints and divide them by the number of patterns that include available
information (Pdim).
2. Use formula 1 to measure the individual learning style (lsdim).
3. Use formula 2 to find (nlsdim), by normalizing the measure result from formula 1 on
a range from 0 to 1.
!"#!"# !!!"#!!
!!! (1)
!"#!"# !!"!"#!!
! (2)
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Where 1 indicates a strong positive preference and 0 indicates a strong negative
preference for the respective learning style. If no pattern includes existing infor-
mation, no information about the learning style can be found.
The AML system will update the Learning Style Module with new information.
Once a Learning Style Module is updated, the AML system will deliver only the
learning content that is suitable to the student’s learning style.
8 Adaptive Learning System Prototype
The main characteristic of our AML (Adaptive Mobile Learning) system is that it
can predict the student’s optimal learning process based on the student’s relevant
background information, prior knowledge, learning preferences and student’s learning
style. Through the implantation of our algorithms, the AML system identifies a stu-
dent’s optimal shortest learning path.
This AML system was designed using System Interface, an Adaptive Engine
Module, a Student Profile Module, a Learning Style Module, a Course Content Mod-
ule, a Student Assessment Module, a Domain Concepts Module, and a Learning Path
Generation Module. Fig. 3 illustrates our AML systems architecture.
Fig. 3. Adaptive M-learning System Architecture
8.1 System interface (SI).
System Interface includes Admin Interface Module (AIM), Instructor Interface
Module (IIM) and Student Interface Module (SIM).
Admin Interface Module (AIM). The Admin Interface Module enables the sys-
tem administrator to access the Course Content Module, Student Profile Module,
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Learning Style Module, Course Content Module, Student Assessment Module, and
the Domain Concepts Module.
AIM provides the services for the system administrator to define access control
rules, access privileges [31] [32], maintain student enrollments, user profiles course
schedules, student examination, create course concept units, course material and ar-
chives. AIM, also, provides the services for the system administrator to monitor the
learning progress [33] [34].
The system administrator can also perform a number of system maintenance opera-
tions through various modules. In the Student Profile Module, the system can create,
edit and delete a student profile [34] [35]. The system administrator can create, edit
delete of course material. In Student Assessment Module the administrator manages
exams [36].
Instructor Interface Module (IIM). The Instructor o Interface Module allows in-
structors to manage and control course subject pages [37], create and modify course
material, manage and control online learning activities, and monitor students’ perfor-
mance based on all types of exams and grading.
Through the Instructor Interface Module an instructor controls the active period
that a student can access each lesson’s or exam. This Module prevents students from
advancing to new lesson contents. A student must finish any test or exercises related
to the student current course content [38].
Student Interface Module (SIM). The Student Interface Module presents the ed-
ucational material to the student in the most effective way. Through the SIM, students
enter their personal information that is then will be saved to their profile database. As
a first time user, SIM prompts the student to take pre-test. This pre-test evaluates the
student’s knowledge, and the results are stored in the student’s profile.
The system will invoke the Adaptive Engine Module which creates and provide
personalized learning paths, according to Student Profile Module and Learning Style
The student has option to attend one of the available course units or search for a
specific unit in order to that the system will provide one or more optimal learning
path. The student selects one of these learning paths and attends his course.
8.2 Student Profile Module (SPM)
A Student Profile Module is the key resource for facilitating our AML system pro-
cess that represents essential information about each student.
The Student Profile Module quantify the student’s relevant background, prior
knowledge, learning preferences, learning style linked to Learning Style Module and
student’s personal information. Each student has his own profile which enables the
system to deliver personalized course learning path with customized course materials,
on the basis of the student’s learning style [39].
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
8.3 Learning Style Module (LSM)
It is observable that different students have different preferences, needs and differ-
ent ways to learn [40]. According to these differences learning style indicates how a
student learns and likes to learn [41] or the perception that individuals differ in regard
to what type of instruction or study is the most effective for them [42].
Our Learning Style Module predict the learner’s behavior uses Felder and Silver-
man for engineering student’s module to classifies students according to where they
fit on a number of scales belonging to the ways in which they receive and process
information, the dimensions of the learning styles in this module, namely perception,
input, processing, and understanding [43] [44].
When students are registered in the system, their learning styles need to be tested.
The student needs to answer a short assessment that is used to determine student’s
preferred learning style [45]. This style indicates a preference for some media type
over others. The assessment results are stored in the Learning Style Module, which
will be used for the initial adaptation in our system.
8.4 Domain Concept Module (DCM).
The Domain Concept Module is divided into two interconnected sub Modules:
" Concept sub-Module. Concept sub Module contains the information about the
domain and the course structure. Our Domain Concept Module was built based on
a weighted directed graph, where each node represents a course unit while arcs rep-
resented relationships between course units as introduced in Section I Learning
Path Graph.
" Media Resources sub-Module (MRM). The system used media Resources sub-
Module to trace media preference where each concept in Concept sub Module
composite with different media types such as audio, video, text, pdf etc. in this way
we provide the students with the best media that represent the course units accord-
ing the students learning style [46].
8.5 Course Content Module (CCM)
All the course units’ materials are stored in databases contained in the Course Con-
tent Module. In this module is easy to extend the database by adding new topics to
any course unit.
The idea behind the separation the Domain Concept Module and Course Content
Module is to make it possible to reuse part or all of the course unit’s material if we
need to use these materials to build a new course with same related materials.
8.6 Learning Path Generation Module (LPM)
The graph in the Domain Concept Module containing all possible learning paths,
the Learning Path Generation Module has all the available personalized learning paths
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
generated from Adaptive Engine Module according to student profile and his learning
8.7 Student Assessment Module (SAM)
In our adaptive mobile learning system prototype the Student Assessment Module
is used to adapt the needs and traits of the students [47], according to student perfor-
mance assessment we can dynamically generate suitable learning content fit the stu-
dent needs.
An online Assessment can be designed to begin with a pre-test, which is an as-
sessment of student pre knowledge of each learning unit before taking the course.
Based on the pre-test results the system only presents to the student the cores unite
that he needs to study according to the learning objectives of the course. Also, there is
post-test for each unit that the student must pass in order to receive credit for each
8.8 Engine Module (AEM)
The Adaptive Engine Module is algorithms that integrate information from the
preceding modules in order to select appropriate learning path to present the course to
the students [48].
An Adaptive Engine Module incorporates the adaptive algorithms of an adaptive
M-Learning system by combining all Modules in order to select appropriate learning
path to present the course to the students. The process of adaptive module starts with
selecting representative nodes by analyzing the student needs from the Student Profile
Module, Learning Style Module and Student Assessment Module [49].
The Adaptive Engine Module performs two tasks, the first task is find all the per-
sonal learning paths using adaptive algorithm detailed in section II incorporates with
the Student Profile Module and Student Assessment Module, so the student selects
one of the optimal paths and attends his course. Second task is retrieves the related
teaching material according to student learning style.
9 Experiment and Results
In order to verify the analytical research results, experimental results are intro-
duced in this section. For this experiment, we have used the Network Security course
CPEG 561. CPEG 561 is a graduate course offered as an elective course for Computer
Science and Computer Engineering students.
This work proposes that our AML system improves the student’s performance
more than control system. This section summarizes the statistical power analysis
performed with the aim to test of the alternative hypothesis.
Let Mx denote the mean for the AML group and My denote the mean for the Con-
trol group.
The statistical Hypotheses for this work are as follows:
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
H0: Mx # My = 0
Ha: Mx # My > 0
The difference significance is determined by the used Level of Significance ($),
Significance level: $ = 0.05.
9.1 T-test
The Student's t-test is used to assesses whether the mean (average) of two groups
are statistically different from each other [50] [51].
Pre-test. The Pre-test was designed to ensure that both the Control group and the
Experimental group had the equivalent computer knowledge required for taking the
Network Security course. The examination questions of the Pre-test included 25 mul-
tiple choice questions and true-false questions covering the content of tested units of
Network Security course.
Question: What was the average Pre-test score for the two groups: AML experi-
mental group and Control group?
As shown in Fig. 4, we have examined the Pre-test results of the AML experi-
mental group (N=15) and the Control group (N=15). For the AML experimental
group, the average score was 57.87. For Control group the average score was 67.20.
Fig. 4. Experimental Group and Control Group Pre-test Comparison Graph.
Question: When comparing the Pre-test results of the two groups, was there a sig-
nificant difference in scores (either positive or negative)?
Table 8 and Fig. 5 present the t-test results of the Pre-test for both groups. As
shown in Table 8, the mean of the Pre-test was 57.8667 and the standard deviation
was 11.8916 for the AML experimental group. Whereas, the mean was 67.20 and the
standard deviation was 13.8729 for the Control group. The p-value result indicates
that the two groups do not significantly differ from each other at p < 0.05. Clearly, it
is evident that the two groups of students have statistically equivalent abilities in
learning of the Network Security course.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Table 8. T-test Results of Pre-test.
Fig. 5. Pre-test Confidence Intervals and Estimated Difference.
Post-test. The Post-test was proposed to compare the learning achievements of two
groups of students after taking the Network Security course. The Post-test contained
three essays and 90 multiple choice/ true-false questions that covered all of the units
of the Network Security course.
Question: What was the average Post-test student’s score for AML experimental
group and Control group?
We examined the Post-test of the AML experimental group (N=15) and the Con-
trol group (N=15). As shown in Table 9, the average score was 66.56 for the AML
experimental group. The average score was 45.97 for Control group.
Question: When comparing post-test student’s scores was there a significant dif-
ference in scores (either positive or negative)?
We compared the Post-test student’s scores for AML experimental group and Con-
trol group (N=30), based on 15 students per group. The average Post-test was 66.558
for AML experimental group, and the average Post-test was 45.9707 for the Control
group, yielding a difference of +20.5873 as shown in Fig. 6. While this difference is
positive, it was also found to be statistically significant. When a correlation was per-
formed, the post-tests for both groups were significantly correlated at the 0.05 level
(p=.05) as shown in Table 9, meaning that the tests measure the same units for both
groups. Further, the results of a t-test yield significance at the .05 level (p<0.05),
meaning that for the whole groups the difference between the post-tests average score
for both groups was statistically significant. In order to obtain the magnitude of the
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
difference between the means of the two groups, we need to calculate Cohen’s d. as
shown in Table 10. The Cohen’s d is approximately 1.60. These results show that the
magnitude of the difference between the groups is called a very large effective size,
besides being not only statistically significant with a difference at p < 0.05.
Table 9. T-test Results of Post-test.
Fig. 6. Post-test Confidence Intervals and Estimated Difference.
To make the decision: t value and Critical values are used. If t value is greater than
Critical t (Probability Ho is True is Low), Reject Ho. In this test, the critical value for
t with degrees of freedom = 28 and $=0.05 is 2.0548, the calculated t exceeds the
critical value (4.3821>2.048), so the means of AML experiment group and control
group are significantly different at p < 0.05. This means Reject Ho and Accept Ha that
our AML system improves the student’s performance more than control systems. It is
evident that the difference is positive, and that our AML prototype improves the stu-
dent’ performance of AML experimental group more than the Control group.
9.2 One-way ANOVA.
The one-way analysis of variance (ANOVA) is used to determine whether there are
any significant differences between the means of two or more independent groups.
We use the one-way (ANOVA) to compare the means between the AML experi-
mental group and the Control group to determine whether these means are significant-
ly different from each other [52] [53]. Here, we will test the null hypothesis:
H0: Mx # My = 0.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Table 10. Cohen's D and the Effect-size Correlation, RY!
Table 11. One-way ANVOA Test Results of the Post-test.
The F ratio is the ratio of two mean square values. Where F (1,28) = 19.203 as
shown in Table 11. Since the F ratio is greater than 1, the results show the means of
the AML experiment group and the control group are significantly different at p <
0.05. Based on the hypothesises of Reject Ho and Accept Ha, our AML system im-
proves the student’s performance more than control systems.
10 Conclusion and Future Work
The purpose of developing an online learning system is to discover the most effec-
tive learning path for any university student enrolled in computer science and engi-
neering courses. We accomplished this task through our design of the AML system
prototype. Our AML system prototype identifies the best learning path through the
implementation of the shortest path algorithm and the designed methods of a student’s
learning style. By performing various Statistical Power Analysis tests, such as t-test,
and one way (ANOVA), we determined that students’ performances from the AML
experimental group had a higher improvement rate than control group. In addition,
our system identified the student’ learning styles and provided the students with dif-
ferent presentations of the learning materials.
Through our experimental results, our proposed AML system prototype positively
enhances the student’s learning process
11 References
[1] Sahai, Priya, and Manuj Darbari. "Adaptive e-learning using Granulerised Agent Frame-
work." International Journal of Scientific & Engineering Research 5.2 (2014).
[2] Thompson, Jim, “Adaptive Learning: Types of Adaptive Learning,” CogBook, 2014.
[4] M. Alian and R. Jabri, "A shortest adaptive learning path in eLearning systems: Mathemat-
ical view," Journal of American Science, vol. 5, pp. 32-42, 2009.
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
[5] I. Zliobaite, A. Bifet, M. Gaber, B. Gabrys, J. Gama, L. Minku, et al., "Next challenges for
adaptive learning systems," ACM SIGKDD Explorations Newsletter, vol. 14, pp. 48-55,
[6] P. Ramteke, Y. Kadam, and S. Gupta, "A Self Adaptive Learning Approach for Optimum
Path Evaluation of Process for Forensic use to finding Uniqueness," Computer Engineer-
ing and Intelligent Systems, vol. 4, pp. 1-6, 2013.
[7] P. Karampiperis and D. Sampson, "Adaptive learning resources sequencing in educational
hypermedia systems," Journal of Educational Technology & Society, vol. 8, pp. 128-147,
[8] C.-M. Chen and C.-J. Peng, "Personalized e-learning system based on ontology-based con-
cept map generation scheme," in Advanced Learning Technologies, 2007. ICALT 2007.
Seventh IEEE International Conference on, 2007, pp. 634-636.
[9] D. J. W. Coffey, "JAVA Programming course Concept Map " in Big Java by Cay Horst-
mann. 4th Edition, ed. University of West Florida, Department of Computer Science ,Java
Programming, COP 2253, 2012.
[10] J. P. Moore, "Promoting Conceptual Understanding via Adaptive Concept Maps," 2013.
[11] J. M. Marquez, J. A. Ortega, L. Gonzalez-Abril, and F. Velasco, "Creating adaptive learn-
ing paths using ant colony optimization and bayesian networks," in Neural Networks,
2008. IJCNN 2008.(IEEE World Congress on Computational Intelligence). IEEE Interna-
tional Joint Conference on, 2008, pp. 3834-3839.
[12] N. V. Anh, N. V. Ha, and H. S. Dam, "Constructing a Bayesian belief network to generate
learning path in adaptive hypermedia system," Journal of Computer Science and Cybernet-
ics, vol. 24, pp. 12-19, 2008.
[13] Li, Da, and Michela Becchi. "Deploying graph algorithms on gpus: An adaptive solu-
tion." Parallel & Distributed Processing (IPDPS), 2013 IEEE 27th International Symposi-
um on. IEEE, 2013.
[14] Alian, Marwah, and Riad Jabri. "A shortest adaptive learning path in eLearning systems:
Mathematical view." Journal of American Science 5.6 (2009): 32-42.
[15] Ramteke, Pallavi, Yashpal Kadam, and Sanket Gupta. "A Self Adaptive Learning Ap-
proach for Optimum Path Evaluation of Process for Forensic use to finding Unique-
ness." Computer Engineering and Intelligent Systems 4.9 (2013): 1-6.
[16] Karampiperis, Pythagoras, and Demetrios Sampson. "Adaptive learning resources se-
quencing in educational hypermedia systems." Journal of Educational Technology & Soci-
ety 8.4 (2005): 128-147.
[17] Yanwen, Wu, and Wu Zhonghong. "Knowledge Adaptive Presentation Strategy in E-
Learning." Proceedings of Second International Conference on Knowledge Economy and
Development of Science and Technology, Beijing. 2004.
[18] Tseng, Shian-Shyong, et al. "An object-oriented course framework for developing adaptive
learning systems." Journal of Educational Technology & Society 11.2 (2008): 171-191.
[19] Makarova, Y., et al. "User profile creation and training mode determination in the “Smart
lab” system." Global Engineering Education Conference (EDUCON), 2014 IEEE. IEEE,
[20] Zhao, Chengling, and Liyong Wan. "A shortest learning path selection algorithm in e-
learning." Advanced Learning Technologies, 2006. Sixth International Conference on.
IEEE, 2006.
[21] Soloman, Barbara A., and Richard M. Felder. "Index of learning styles questionnaire." NC
State University. Available online at: http://www. engr. ncsu. edu/learningstyles/ilsweb.
html (last visited on 14.05. 2010) (2005).
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
[22] Ahmad, Norazlina, et al. "Automatic detection of learning styles in learning management
systems by using literature-based method." Procedia-Social and Behavioral Sciences 103
(2013): 181-189.
[23] J. Feldman, A. Monteserin, and A. Amandi, "Automatic detection of learning styles: state
of the art," Artificial Intelligence Review, vol. 44, pp. 157-186, 2015.
[24] C.A Carver, R.A. Howard, and W.D. Lane, “Enhancing student learning Through Hyper-
media Courseware and Incorporation of Student Learning Style”, IEEE Transactions on
Education, vol. 42, no 1, 1999, pp. 33-38.
[25] S. Graf, K. Shuk, and T.-C. Liu, "Identifying learning styles in learning management sys-
tems by using indications from students' behaviour," in Advanced Learning Technologies,
2008. ICALT'08. Eighth IEEE International Conference on, 2008, pp. 482-486.
[26] E. Popescu, P. Trigano, and C. Badica, "Relations between learning style and learner be-
havior in an educational hypermedia system: An exploratory study," in Advanced Learning
Technologies, 2008. ICALT'08. Eighth IEEE International Conference on, 2008, pp. 725-
[27] H. Hong and D. Kinshuk, "Adaptation to student learning styles in web based educational
systems," in EdMedia: World Conference on Educational Media and Technology, 2004,
pp. 491-496.
[28] N. Van Zwanenberg, L. Wilkinson, and A. Anderson, "Felder and Silverman's Index of
Learning Styles and Honey and Mumford's Learning Styles Questionnaire: how do they
compare and do they predict academic performance?," Educational Psychology, vol. 20,
pp. 365-380, 2000.
[29] M. S. Zywno, "A contribution to validation of score meaning for Felder-Soloman’s index
of learning styles," in Proceedings of the 2003 American Society for Engineering Educa-
tion annual conference & exposition, 2003, pp. 1-5.
[30] T. Lin, "Application of Learning Styles Adaptivity in Mobile Learning Environments," in
Paper presented at the Third Pan Commonwealth Forum on Open Learning, Dunedin, New
Zealand, July 48, 2004.
[31] S. Graf and T.-C. Liu, "Supporting teachers in identifying students' learning styles in learn-
ing management systems: an automatic student modelling approach," Journal of Educa-
tional Technology & Society, vol. 12, p. 3, 2009.
[32] L. Oneto, F. Abel, E. Herder, and D. Smits, "Making today’s learning management sys-
tems adaptive," in Learning Management Systems meet Adaptive Learning Environments,
Workshop at European Conference on Technology Enhanced Learning (ECTEL), 2009.
[33] E. Erturk, "An intelligent and object-oriented blueprint for a mobile learning institute in-
formation system," International Journal for Infonomics, vol. 6, 2013.
[34] K. Palanivel and S. Kuppuswami, "Service-oriented reference architecture for personalized
e-learning systems (SORAPES)," International Journal of Computer Applications, vol. 24,
pp. 35-44, 2011.
[35] K. Van Der Sluijs and K. Höver, "Integrating adaptive functionality in a LMS," Interna-
tional Journal of Emerging Technologies in Learning (iJET), vol. 4, 2009.
[36] A. Riad, H. El-Minir, and H. El-Ghareeb, "Review of e-learning systems convergence
from traditional systems to services based adaptive and intelligent systems," Journal of
Convergence Information Technology, vol. 4, pp. 108-131, 2009.
[37] J. C. Tseng, H.-C. Chu, G.-J. Hwang, and C.-C. Tsai, "Development of an adaptive learn-
ing system with two sources of personalization information," Computers & Education, vol.
51, pp. 776-786, 2008.
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
[38] O Deperlioglu, U Kose, R Yildirim, "A Model of Blended Learning in Computer Engi-
neering Education." Future-Learning 2010, 351-36.
[39] O. Deperlioglu, U. Kose, and R. Yildirim, "Design and Development of an E-Learning
Environment for the Course of Electrical Circuit Analysis," Interdisciplinary Journal of E-
Learning and Learning Objects, vol. 8, pp. 51-63, 2012.
[40] P. García, A. Amandi, S. Schiaffino, and M. Campo, "Evaluating Bayesian networks’ pre-
cision for detecting students’ learning styles," Computers & Education, vol. 49, pp. 794-
808, 2007.
[41] A. Kla%nja-Mili&evi&, B. Vesin, M. Ivanovi&, and Z. Budimac, "E-Learning personaliza-
tion based on hybrid recommendation strategy and learning style identification," Comput-
ers & Education, vol. 56, pp. 885-899, 2011.
[42] Y.-C. Chang, W.-Y. Kao, C.-P. Chu, and C.-H. Chiu, "A learning style classification
mechanism for e-learning," Computers & Education, vol. 53, pp. 273-285, 2009.
[43] H. Pashler, M. McDaniel, D. Rohrer, and R. Bjork, "Learning styles concepts and evi-
dence," Psychological science in the public interest, vol. 9, pp. 105-119, 2008.
[44] R. M. Felder and L. K. Silverman, "Learning and teaching styles in engineering educa-
tion," Engineering education, vol. 78, pp. 674-681, 1988.
[45] G.-J. Hwang, H.-Y. Sung, C.-M. Hung, and I. Huang, "A learning style perspective to in-
vestigate the necessity of developing adaptive learning systems," Journal of Educational
Technology & Society, vol. 16, pp. 188-197, 2013.
[46] A. Kla%nja-Mili&evi&, B. Vesin, M. Ivanovi&, and Z. Budimac, "Integration of recommen-
dations and adaptive hypermedia into Java tutoring system," Computer Science and Infor-
mation Systems, vol. 8, pp. 211-224, 2011.
[47] Y. E. A. Mustafa and S. M. Sharif, "An approach to adaptive e-learning hypermedia sys-
tem based on learning styles (AEHS-LS): Implementation and evaluation," International
Journal of Library and Information Science, vol. 3, pp. 15-28, 2011.
[48] S. F. I. a. S. company. (2012, Learning : Online Exams Adaptive Learning. V0.0.
[50] J. Van Seters, M. Ossevoort, J. Tramper, and M. J. Goedhart, "The influence of student
characteristics on the use of adaptive e-learning material," Computers & Education, vol.
58, pp. 942-952, 2012.
[51] V. Esichaikul, S. Lamnoi, and C. Bechter, "Student modelling in adaptive e-learning sys-
tems," Knowledge Management & E-Learning: An International Journal (KM&EL), vol.
3, pp. 342-355, 2011.
[52] Walpole, R. E.; Myers, R. H.; Myers, S. L. & Ye, K. "Statistics for engineers and scien-
tists ." Probability &amp; Pearson Education , Upper Saddle River, 2007.
[53] Reuven Y. Rubinstein and Dirk P. Kroese."Simulation and the Monte Carlo Method. "
Wiley Series in Probability and Statistics (2 ed.). 2007.
[54] M. Roberts and R. Russo, A student's guide to analysis of variance: Routledge, 2014.
[55] H. Seltman, "Experimental Design and Analysis Available from http://www. stat. cmu.
edu/~ hseltman/309/Book," Book. pdf, 2012.
iJIM Vol. 12, No. 5, 2018
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
12 Authors
Dr. Ibrahim Alkore Alshalabi received his B.Sc. in Computer Science from Al-
Isra Private University, Amman, Jordan in 1997, his Master’s of Computer Applica-
tions (MCA) from Bangalore University, India in 2007, and his PhD in Computer
Science and Engineering from the University of Bridgeport, USA in 2016. From
1997-2004 he was an Assistant Lecturer at Ma'an Community College, Al-Balqa
Applied University, Jordan. From 2007 to 2009 he was an assistant lecturer at Al-
Hussein Bin Talal University, Jordan. He is currently an adjunct Professor at Al-
Hussein Bin Talal University, College of Information technology, Jordan. His re-
search interests are E-Learning, M-Learning, wireless communications, and networks.
He was an active committee member of the International Conference on Engineering
Education, instructional technology, Assessment, and E-Learning (EIAE 2010, EIAE
Dr. Dr. Samir Hamada received his PhD in Computer Science and Engineering
and MS in Computer Science from University of Bridgeport in 2016 and 2001. He,
also, received his B.S. in Accounting from Ain Shams University in Egypt. He is
currently an Assistant Professor of Computer Systems, School of Business at Farm-
ingdale State College in Farmingdale NY, USA. His research interests include Adap-
tive Learning, Mobile Learning and the Semantic Web.
Dr. Khaled Elleithy is the Associate Vice President for Graduate Studies and Re-
search at the University of Bridgeport. He is a professor of Computer Science and
Engineering. He has research interests in the areas of wireless sensor networks, mo-
bile communications, network security, quantum computing, and formal approaches
for design and verification. He has published more than three hundreds research pa-
pers in international journals and conferences in his areas of expertise. Dr. Elleithy is
the editor or co-editor for 12 books by Springer. He is a member of technical program
committees of many international conferences as recognition of his research qualifica-
tions. He served as a guest editor for several International Journals. He was the chair-
person for the International Conference on Industrial Electronics, Technology & Au-
tomation, IETA 2001, 19-21 December 2001, Cairo Egypt. Also, he is the General
Chair of the 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012, 2013, and 2014 Inter-
national Joint Conferences on Computer, Information, and Systems Sciences, and
Engineering virtual conferences.
Dr. Ioana Badara holds a Ph.D. (Teacher Preparation/Science Education) from
University of TennesseeKnoxville and an M.Phil. (Microbiology & Immunology)
from University of Edinburgh, Scotland. Prior to completing her doctoral work, she
has worked as a research scientist in the biomedical field for about ten years, having
been affiliated with Weill Medical College of Cornell University and Mount Sinai
School of Medicine, in New York City. Her passionate interest in the exploration of
connections between scientists’ epistemologies and the teaching of science led her to
pursuing doctoral studies in Science Education. She has taught a multitude of core
Biology courses for Biology/Pre-Medical undergraduates and mentored student re-
search projects in this field. Dr. Badara is currently a faculty member at University of
Bridgeport, where she teaches core research courses in the doctoral (Ed.D.) program,
PaperAutomated Adaptive Mobile Learning System using Shortest Path Algorithm and Learning Style
Science Education courses in the Science Teacher Preparation program, and History
and Philosophy of Science courses at the undergraduate level. She has been the recip-
ient of several grants for research, including a National Science Foundation grant for
conducting research on the teaching of science in urban school districts. She has pre-
sented her work at national and international conferences in the field of STEM educa-
Dr. Saeid Moslehpour is an Associate Professor and Department Chair in the
Electrical and Computer Engineering Department in the College of Engineering,
Technology, and Architecture at the University of Hartford. He holds a Ph.D. (1993)
from Iowa State University and bachelors of science (1989) and masters of Science
(1990) degrees from University of Central Missouri. His research interests include
logic design, CPLDs, FPGAs, embedded systems, electronic system testing, and
Article submitted 29 December 2017. Resubmitted 21 January 2018. Final acceptance 03 April 2018.
Final version published as submitted by the authors.
iJIM Vol. 12, No. 5, 2018
... Full-text articles assess for eligibility (n = 60) Learning style E-learning [7], [24], [33]- [36], [25]- [32] Learning style Mobile learning [37], [38] Learning style E-learning and traditional educational [39] Learning style, initial knowledge and motivation E-learning [40] Learning style, knowledge level, prior knowledge, learners' preferences E-learning -DAHS [41] Cognitive styles; learning behaviour and browsing behaviour E-learning [42] Learning style and learning motivation E-learning [43] Learning style and cognitive level Blended learning [44] Learning style and dyslexia type E-learning [45] Learner's performance (assessment activities), knowledge level and assessment pattern E-learning [46] Cognitive style Mobile learning [47] Learning Another statistic generated from Table II's results is the number of student characteristics employed in the adaptive learning system. The comparison of studies using one of the student's characteristics with studies using multiple student characteristics is shown in Figure 3. ...
... Learning style VARK questionnaire [29], [36] Learning style ILS questionnaire [18], [19], [40], [41], [43]- [45], [25], [26], [28], [32]- [34], [37], [ [53] ...
... This finding was supported by other studies such as [16] and [13]. Numerous benefits come from knowing a student's preferred learning style, including the ability to assign projects automatically by their preferences, expectations, and demands [24] and personalizing learning materials for students [37]. The study's findings also showed that, although learning styles are a common feature of students, they may be combined with other traits. ...
Adaptive learning allows students to learn effectively based on their abilities and characteristics at their own pace. Currently, numerous SLRs exist regarding students' adaptive learning characteristics, analyzed from various perspectives by previous researchers. However, it is essential to note that the findings of these studies are based on analyses conducted between 2010 and 2020. This SLR aims to extend and bridge the gaps in identifying essential student characteristics for implementing an adaptive learning system. It specifically focuses on the most recent five-year period, from 2018 to 2022. This study chose 39 articles according to the specified inclusion and exclusion criteria. The findings from the SLR indicate that learning style is the most commonly used element of adaptation in the reviewed articles, followed by knowledge characteristics, cognitive traits, student preference, and motivation. This SLR also revealed that most of the reviewed articles used more than one student's characteristics in modeling the student model, and results show that educators integrated online learning for implementing adaptive learning in the teaching and learning process. The ILS instrument, which is traditional detection, is widely used in collecting learning style data, and besides FSLSM, other learning style models, including VARK, Kolb, and Honey & Mumford, are used to assign students' learning style preferences.
... The learning apps contain a repository of learning materials which may include documents and media, that are presented to the user. To manage these learning materials a weighted directed graph has been used in Alshalabi et al. [20]. In studies like Garcia-Cabot et al. [21] Multi-Agent systems have been used to manage the course content. ...
... The user roles and access grants are usually provided through the application's interface where users may or may not be able to see different items of the app based on the user role. The study by Alshalabi et al. [20] contains three sub-modules connected to the System Interface Module, namely, the Admin Interface Module, Instructor Interface Module, and Student Interface Module. Moreover, Yarandi et al. [23] have presented separate modules for each user (Learner and Instructor), where the Learner and Instructor access the system through a User Interface Manager and a Courseware Manager, respectively. ...
... The two main users who can interfere through the User Interface are "Student" and "Teacher". The Teacher is allowed to create, view, update, and delete Lessons, as well as to view students' progress [20]. The Student can enroll in Lessons, follow them and respond to activities, and finally view the results. ...
Conference Paper
Full-text available
At present, a significant demand has emerged for online educational tools that can be used in replacement for classroom education. Due to the ease of access, the preference of many users is focused on m-learning applications. This paper presents an architectural framework for an interactive mobile learning toolkit. This study explores different software design patterns and presents the implementation details of the prototype. As a case study, the application is applied for the primary education sector in Sri Lanka, as there is a lack of adaptive learning mobile toolkits that allow teachers and students to interact effectively. The study is concluded to be user-friendly, understandable, useful, and efficient through a System Usability Study.
... The evaluation results indicated that the experimental group had a much higher course completion rate (36%) in comparison with the control group (3%). Likewise, Alshalabi et al. (2018) used an A/B test to evaluate an adaptive algorithm providing personalized course content sequences considering different LSs. This test included a pre-and a post-test questionnaire. ...
... Assessments were often conducted with data from universities' learners in similar disciplinary contexts. The contexts were mostly related to the computer field, including computer science El-Aissaoui et al., 2018a;Sheeba & Krishnan, 2018;Alshalabi et al., 2018;Hassan et al., 2019;Gomede et al., 2020), computer technology (Abdullah, 2015;Maaliw et al., , 2020Maaliw, 2016aMaaliw, , 2016bShamsudin et al., 2018Shamsudin et al., , 2019, procedural programming (Karagiannis & Stratzemi, 2020), artificial intelligence (Dung & Florea, 2012a;García et al., 2007García et al., , 2008, statistical learning (b; Hmedna, 2019a), data structure (Ahmad & Shamsuddin, 2010), bioinformatics (Li et al., 2018), and introduction to information technology (Liyanage et al., 2014). Besides these, there were a few datasets from other contexts, such as data from an English course (Hidayat et al., 2020), a driving license program (Ali et al., 2018), and a speech therapy course (Ferreira et al., 2018). ...
Learning systems, whether traditional or computerized ones, often have a teacher-based design and use a “one-size-fits-all” approach. This approach ignores learners’ differences and preferences, which results in demotivating learn- ers and decreasing their engagement with a course. Subsequently, it increases their dropout rate (i.e. withdrawing from a course). One of the solutions to tackle these issues is delivering learning materials to learners considering their learning styles. Learning style indicates the way that each learner prefers to receive learning materi- als and interact with a learning environment. To this end, in this paper, we present a comprehensive review on methods that are proposed for the automatic predic- tion of learning styles. We start by explaining the methods and algorithms for the learning style prediction and categorize them into literature-based and data-driven approaches and describe their pros and cons. We also explore the data and learn- ing attributes used by these approaches for the prediction task. In addition, we pre- sent online and offline evaluation approaches to assess the prediction methods and describe their advantages and disadvantages. Finally, we discuss the main challenges and possible research directions in the area of learning style prediction approaches, which need to be considered to enhance the quality of research in this area.
... This approach is more generalized and can be used with data from any course. This method has been utilized by several researchers to identify learners learning styles [15], [16], [17], [18], [19]. However, the approach may have inaccurate because assessing the importance of different cues when determining learning styles is challenging. ...
Full-text available
Prediction of learners' learning styles in online environments has several advantages, including steering learners on the proper path, motivating and engaging them while learning, and improving their learning results. It also helps instructors in the formation of personalized resource recommendations. As a result, predicting learners learning styles is necessary to aid in the personalization process. Existing approaches use either conventional or automatic approaches for learning style identifications. However, the large volume of data stored in online platforms has become a challenge in analyzing the behavior of learners and predicting their learning styles in the real world. Also, most of the existing approaches rely on a particular learning platform and can not be used in other platforms without technical assistance. In this paper, we propose GNN-LS, a new approach to identify and predict learners learning styles using a graph neural network. First, the graph embedding technique is used to capture the representation of learners and resources as a bipartite graph and encode them into low-dimensional representation. The encoded L-R sequences were given as input to the K-means clustering algorithm to identify and obtain labels as per FSLSM dimensions. Then, Graph neural network is trained to predict the learner's learning style in the real world. The GNN-LS technique can be applied in a variety of educational systems and adapted to fit a variety of learning style models. Extensive experiments are run using the 2015 KDD Cup public available dataset to demonstrate the capabilities of GNN-LS. 5.31-15.68% improvements are achieved across all four FSLSM dimensions in accuracy.
... This learning path graph represents and describes the structure of domain knowledge, including the learning goals, and all available learning paths. [7] also proposes a system prototype that implements an adaptive learning path algorithm that uses the student s information from their profile and their learning style to improve the students learning performances through a mobile learning system that provides a suitable course content sequence in a personalized manner. ...
Conference Paper
Full-text available
The paper presents a design of a mobile serious game, suitable for primary school students, consisting of a set of tasks for solving. The design offers adaptability in terms of the learning process (learning sequence) and content. Adaptability is realized depending on the success/failure of the students and spent time for solving the tasks, the task difficulty and task type. The motivation of the learner is provoked by collecting points and virtual objects. To experiment the applicability of the design, a prototype of an educational math game for the third-grade students based on the templates (12 kinds of elementary games, suitable for mobile realization and this age group) is created. Math problems are presented in different game levels, where students can collect coins and gold bars, depending on their learning progress.
... To achieve this, an adaptive knowledge assessment system that would propose questions based on previous correct and/or incorrect answers in real-time is needed. However manual design and monitoring of students' learning paths are resource-consuming and time-inefficient tasks, and automation is preferable in this area [6]. In adaptive learning, the same learning material might be presented in a different form or different order to provide an individualized learning path. ...
Full-text available
The COVID-19 pandemic and quarantine have forced students to use distance learning. Modern information technologies have enabled global e-learning usage but also revealed a lack of personalization and adaptation in the learning process when compared to face-to-face learning. While adaptive e-learning methods exist, their practical application is slow because of the additional time and resources needed to prepare learning material and its logical adaptation. To increase e-learning materials’ usability and decrease the design complexity of automated adaptive students’ work evaluation, we propose several transformations from a competence tree-based structure to a graph-based automated e-evaluation structure. Related works were summarized to highlight existing e-evaluation structures and the need for new transformations. Competence tree-based e-evaluation structure improvements were presented to support the implementation of top-to-bottom and bottom-to-top transformations. Validation of the proposed transformation was executed by analyzing different use-cases and comparing them to the existing graph-to-tree transformation. Research results revealed that the competence tree-based learning material storage is more reusable than graph-based solutions. Competence tree-based learning material can be transformed for different purposes in graph-based e-evaluation solutions. Meanwhile, graph-based learning material transformation to tree-based structure implies material redundancy, and the competence of the tree structure cannot be restored.
... To describe the structure of domain knowledge, including the learning goals, and all other available learning paths, this study has proposed a learning path graph (LPG) inscribed in a system prototype that implements adaptive learning path algorithms. The proposed algorithms use students' information from their profiles and their learning style to improve academic performance within an m-learning system that provides a suitable course content sequence in a personalized manner [32]. Many investigations are devoted to analyzing the capabilities of mobile applications that can advance learning and develop students' professional skills. ...
Full-text available
p class="0abstract">Over the past few years, the teaching process has transformed radically under significant investments in information and communication technologies. In this context, mobile technologies emerge as an innovative educational tool. Mobile devices are being used by a vast number of so-called "digital generation" representatives in daily life and educational activities. It has been proven that the implementation of mobile technologies in education contributes to the increase of students' motivation, participation in the learning process, and faster acquisition of professional competencies. These technologies take the role of the "driving force" in training. However, their comprehensive understanding is essential to use them effectively. The objective of this study was to analyze the intensity of mobile technologies' use and investigate their evolution in higher education using the example of the I.M. Sechenov First Moscow State Medical University. The research sample was represented by 151 students (data collected for 2015/2016) and 274 students (data for 2019/2020). The average participants' age corresponded to 19.8. The study also involved three experts who were required to evaluate questionnaires completed in Google Forms. The scientific method of the study was based on the organized examination, strict control over the involved respondents, and quantitative research. The research outcomes were analyzed through Chi-Square goodness-of-fit test. The target questions of the survey were rated on a 5-point Likert scale. According to the study results, 95% of the respondents used mobile devices for educational purposes, of which 65% agreed with the convenience of having course materials on a mobile device. In the 2015/2016 academic year, the share of students using smartphones for learning comprised 10.4%, while in 2019/2020, their percentage increased to 61.5%. The study findings will be useful for university teachers and representatives of educational institutions' administration.</p
Conference Paper
Full-text available
Online education has inevitably become the trend for education supporting distance learning. However, due to the transformation from traditional teaching to online mode, effective teaching has become a challenge. This paper proposes an m-learning toolkit compose of a video-based learning content authoring framework that allows the creation of interactive and adaptive learning content. This paper explores the features that assist to achieve the intended outcome and implements chosen features to fulfil the limitations of existing applications. The evaluation of the application shows a good system usability score of 81.7% and supports interactivity, user-friendliness, efficiency, easiness, and understandability.
A curriculum sequence represents a match between learners’ preferences, needs, and surroundings from one side, and the learning content characteristics and the pedagogical requirements from the other side. The curriculum sequence adaptation problem (CSA) is considered as an important issue in adaptive and personalized learning field. It concerns the dynamic generation of a personal optimal learning path for a specific learner. This problem has gained an increased research interest in the last decade, and heuristics and meta-heuristics are usually used to solve it. In this direction, this paper summarizes existing works and presents a novel GA-based approach modeled as an objective optimization problem to deal with this problem. The experimental results from simulations showed that the proposed GA could outperform particle swarm optimization (PSO) and a random search approach in many simulated datasets. Moreover, from a pedagogical perspective, positive learners’ feedback and high acceptance towards the proposed approach is indicated.
Full-text available
This paper presents an approach to integrate learning styles into adaptive e-learning hypermedia. The main objective was to develop an adaptive e-learning system and assess the effect of adapting educational materials individualized to the student’s learning style. The proposed approach utilized adaptive hypermedia technology to improve learning process by adapting course content presentation to student learning styles. The combination of Apache, MySQL and PHP were used to implement the system based on learning styles to present the appropriate subject matter, including the content, format and media type. The system was organized into 3 models; domain model, learner model and adaptation model. The 3 models interact together to perform adaptively. An experiment between 2 groups of students was conducted to evaluate the impact on learning achievement. Inferential statistics were applied to make inferences from the sample data to more general conditions. Descriptive statistics were applied simply to describe what's going on in the sample data. Results showed that students taught using learning style adaptive system performed significantly better in academic achievement (p<0.05) than students taught the same material without adaptation to learning style. The findings support the use of learning styles as guideline for adaptation into the adaptive e-learning hypermedia systems. Key words: E-learning, adaptive hypermedia, learning styles, technology based education, academic achievement.
Full-text available
Learning styles are considered to be one of the factors that need to be taken into account in developing adaptive learning systems. However, few studies have been conducted to investigate if students have the ability to choose the best-fit e-learning systems or content presentation styles for themselves in terms of learning style perspective. In this paper, we aim to investigate these issues by using two versions of an educational game developed based on the sequential/global dimension of the learning style proposed by Felder and Silverman. The experimental results showed that the choices made by the students were not related to their cognitive process or learning style; instead, most students made their choices by intuition based on personal preferences. Moreover, the students who learned with learning style-fit versions showed significantly better learning achievement than those who learned with non-fit versions. Consequently, it is concluded that students preferring one game over another does not necessarily mean that they will learn better with that version, revealing the importance and necessity of developing adaptive learning systems based on learning styles. © International Forum of Educational Technology & Society (IFETS).
Full-text available
Previous studies showed that automatic approach as a better approach to identify learning style in online learning because it is based on the actual students’ behaviour pattern while learning. However, there are several methods in an automated approach can be used to identify learning styles and literature-based method is said to be practical by using LMS. Therefore the purpose of this study is to identify the learning style based on patterns of behaviour for 20 students who studied Interactive Multimedia course within LMS environment in the context of Malaysian polytechnic student. Patterns of behaviour were analyzed based on literature-based method. The Findings indicate the predicted and ILS learning style are different because it depends on the actual behaviour patterns of students. Therefore, identifying learning styles literature-based method is needed to ensure the measurement is based on actual student behaviour during online learning.
Full-text available
A learning style describes the attitudes and behaviors, which determine an individual’s preferred way of learning. Learning styles are particularly important in educational settings since they may help students and tutors become more self-aware of their strengths and weaknesses as learners. The traditional way to identify learning styles is using a test or questionnaire. Despite being reliable, these instruments present some problems that hinder the learning style identification. Some of these problems include students’ lack of motivation to fill out a questionnaire and lack of self-awareness of their learning preferences. Thus, over the last years, several approaches have been proposed for automatically detecting learning styles, which aim to solve these problems. In this work, we review and analyze current trends in the field of automatic detection of learning styles. We present the results of our analysis and discuss some limitations, implications and research gaps that can be helpful to researchers working in the field of learning styles.
Most e-Learning systems provide web-based learning so that students can access the same online courses via the Internet without adaptation, based on each student's profile and behavior. In an e-Learning system, one size does not fit all. Therefore, it is a challenge to make e-Learning systems that are suitably "adaptive". The aim of adaptive e-Learning is to provide the students the appropriate content at the right time, means that the system is able to determine the knowledge level, keep track of usage, and arrange content automatically for each student for the best learning result. This study presents a proposed system which includes major adaptive features based on a student model. The proposed system is able to initialize the student model for determining the knowledge level of a student when the student registers for the course. After a student starts learning the lessons and doing many activities, the system can track information of the student until he/she takes a test. The student's knowledge level, based on the test scores, is updated into the system for use in the adaptation process, which combines the student model with the domain model in order to deliver suitable course contents to the students. In this study, the proposed adaptive e-Learning system is implemented on an "Introduction to Java Programming Language" course, using LearnSquare software. After the system was tested, the results showed positive feedback towards the proposed system, especially in its adaptive capability.
The purpose of this conceptual paper is to develop an original framework that summarizes the applicable software model, and guiding approaches and principles for designing a comprehensive information system for a mobile learning institute. Artificial intelligence has played a role in various strands of computer-mediated education, including e-learning learning platforms. In adaptive delivery mode, learning applications simulate the behavior and interaction of human teachers. AI functionality can be incorporated into mobile learning because mobile devices have the processing power and operate in wireless networks. In addition, the individual elements of the framework are illustrated in industry-standard Unified Modeling Language diagrams. A review of educational and artificial intelligence literatures shows how these fields are related and helps identify techniques to develop smart mobile learning applications. An overview of mobile learning application design helps build a theoretical foundation in this area. The individual parts of the proposed framework are: the architectural framework, cognitive framework, project definition framework, application design framework, and organizational framework. The organizational framework lays the conceptual foundation for creating and implementing an information system within a newly established mobile learning institute. This paper fills a gap in the literature as there is currently no comprehensive overview of this topic. Furthermore, there are currently no existing schools, organizations, or individual departments within that focus only on and provide mobile learning. In addition to fostering the development of such a mobile learning institute, the proposed framework is also useful for guiding technical work on content design.