Towards a Model of Self-regulated e-learning and Personalization of Resources

Abstract

E-learning systems, also called virtual learning environments, promote education and training activities using modern information and communication technologies. Therefore, e-learning is the application of modern multimedia technologies and the Internet to improve the quality of learning by making resources and services more accessible, as well as exchanges and collaboration at a distance that can help learners in their studies and that can also help teachers to predict the weaknesses, strengths, and level of understanding of learners. Preparing and providing a quality e-learning system and rich learning experience are significant challenges. The lack of interaction, feedback, helping the learner to self-regulate, assessing the degree of knowledge, and adapting teaching methods and resources to the learners’ real needs, which imply a lack of motivation and a high dropout rate, diminish the richness of the learning experience. Hence, we propose in this article a robust model of adaptive e-learning environments to optimize learning for each learner, taking into account the heterogeneity of profiles so that students succeed in their learning experiences.

Full text

Towards a model of self-regulated e-learning and
personalization of resources
Wijdane Kaiss1, 2, Khalifa Mansouri1 and Franck Poirier2
1 Laboratory Signals, Distributed Systems and Artifical Intelligence ENSET Mohammedia,
University Hassan II of Casablanca, Morocco
2 Lab-STICC, University Bretagne Sud, Vannes, France
wijdanekaiss@gmail.com
khmansouri@hotmail.com
franck.poirier@univ-ubs.fr
Abstract. E-learning systems, also called virtual learning environments, are
systems that promote education and training activities using modern infor-
mation and communication technologies. Therefore, e-learning is the applica-
tion of modern multimedia technologies and the Internet to improve the quality
of learning by making resources and services more accessible, as well as ex-
changes and collaboration at a distance that can help learners in their studies
and that can also help teachers to predict the weaknesses, strengths and level of
understanding of learners. Preparing and providing the quality e-learning sys-
tem and rich learning experience are major challenges. The lack of interaction,
feedback, helping the learner to self-regulate, assessing the degree of
knowledge and adapting teaching methods and resources to the real needs of the
learners which imply a lack of motivation and a high dropout rate, diminish the
richness of the learning experience. Hence, we propose in this article a robust
model of adaptive e-learning environments to optimize learning for each learn-
er, taking into account the heterogeneity of profiles so that students succeed in
their learning experiences.
Keywords: E-learning, Personalization, Self-regulated learning, Learner learn-
ing experience, Learner success.
1 Introduction
Today, online learning has outgrown the traditional classroom environment. Due to
the spread of the coronavirus pandemic, LMS (Learning Management System) has
experienced unprecedented growth should continue to develop and evolve in the com-
ing years. Most students feel less stress as a result of online learning and feel more
comfortable emotionally [1].
Unfortunately, distance education poses pedagogical issues that reduce the rich-
ness of the learning experience. Prepare and provide a quality system and a rich learn-
ing experience are major challenges. The separation of the physical and temporal of
the tutor and the learner, and between the learners themselves, can lead to a feeling of

2
isolation and a lack of discussion and interaction and feedback that generally concerns
the learners' communication mechanisms with their teachers and peers. These gaps
can reduce the richness of the learning experience. Whereas, peer teaching contributes
to improving student success [2]. For the learner, distance education requires good
organization and pursuit of goals so that he/she succeeds in his/her training. Dropout
rates from online courses are high due to the inability to self-regulate [3], this may be
due in part to the fact that students underestimate the effort involved and fail to
properly plan their work to be successful in online courses. Distance education poses
another issue, which consists of evaluating the student's degree of assimilation of the
material taught. This evaluation is essential if we want to accompany the learner and
ensure concrete progress, it allows students to determine which parts of the course
they need to study and it allows instructors to know what course content needs to be
adjusted.
In addition, e-learning environments do not always present the resources most
suited to the real needs of learners such as the language of teaching, what they want to
learn, the need to work with peers or individually, the type of questions, and type of
learning objects (e.g. video, image, text, etc.). Not all of these needs are automatically
detected, which implies a lack of motivation among learners and a high dropout rate
that can reduce their success rate in these e-learning systems. Thus, all students learn
best when teachers adapt the teaching methods, resources, and learning environment
that suit their interests, needs, strengths, and level of knowledge. But even for the best
teachers, it is difficult to fully understand each learner's profile and adapt the program
accordingly and help them to self-regulate. This is why technology could be of great
use; therefore using it adds new possibilities for tracking learners' activity and provid-
ing them with more immediate feedback on their progress. Hence, the conclusion that
one of the main axes is the personalization of learning that must be taken into account
if we want to see student outcomes improve.
To resolve these issues, we judged that it is essential to include personalization,
evaluation, feedback, help the learner to self-regulate, etc. while adapting them to the
learner's profile (knowledge, preferences, abilities, objectives, etc.) due to their im-
portance. In this article, we propose a model of e-learning environments, personalizing
the pedagogical resources so that students succeed in their learning experiences. Ra-
ther than imposing a unique program on all learners independently of their respective
abilities and needs, personalized learning allows the development of individualized
learning that they will motivate them to follow.
The article is structured as follows: The following section reviews the literature on
key theories and models presenting several factors that can contribute to the use, en-
gagement, satisfaction, and success of learners in the e-learning system. Our proposed
model is presented in Section 3. Subsequently, the proposed approach is described in
detail in section 4. Then, we will end our article with a conclusion and a presentation
of our future research work.
2 Related Work
A large number of studies over the recent decades have attempted to identify the suc-
cess factors of e-learning that need to be managed to increase the effectiveness of e-

3
learning systems.
According to [4], the e-learning success model adequately explains and predicts
the interdependence of six critical success factors for e-learning systems including
course design quality, instructor involvement, student motivation, student-student
dialogue, student-instructor dialogue, and self-regulated learning. Several researchers
have been interested in aspects of the learner and how they can influence the learning
process. Some have looked at personal characteristics such as learning styles [5] or
motivation such [6] and claimed that these have an important influence on the success
or failure of learners. According to [7] the effectiveness of learner-controlled online
learning depends on individual cognitive characteristics and related to motivation such
as learning styles, cognitive abilities, attribution of success, and self-regulation abili-
ties.
Motivation is essential to learning and what really makes students learn is their
conscious engagement in these learning activities, because "engagement leads to out-
comes such as success" and "motivation underlies engagement", engagement and
motivation are not the same [8]. Motivation can be transformed into engagement with
an appropriate design of support. According to [9] intrinsic value and self-efficacy are
motivation variables, whereas effort and metacognitive regulations are regulation
variables, and cognitive and emotional engagements are engagement variables. Sup-
porting students' effort regulation is a unique way to improve the motivation and en-
gagement that influences their success and it is the metacognitive and effort regulation
that learners put into the process of their learning that transforms motivation into en-
gagement [9].
The word "self-regulation" refers to a student's ability to regulate his or her
thoughts and actions [10]. For example, students can reflect more about how they
learn and what strategies they will need to succeed in their university studies. To
achieve specific learning and performance goals, a self-regulated learner employs
motivational, metacognitive, and behavioral processes (for example, help-seeking,
goal setting, self-evaluation, and metacognitive monitoring) [11], [12]. Self-regulation
processes considered motivating allow a learner to initiate and maintain targeted activ-
ities focused on objectives while ignoring distractions and setbacks [13].
A self-regulated learner actively engages these processes by using strategies in
what [10] have called Self-Regulated Learning Strategies (SRLS) [10], [14]. Exam-
ples of SRLS include tutoring, keeping a study journal, and emailing the instructor.
Additionally, not all self-regulated learners use the same strategies. Thus, empirical
research has shown that implementing various strategies in online courses can pro-
mote SRLS in students and that structuring the e-learning environment to promote
self-regulated learning is a central element to fostering the successful use of SRLS by
students [15], [16]. Researchers have suggested that SRLS are of greater importance
in e-learning environments due to their more autonomous nature [17]. Thus, providing
self-regulated learning strategies to online instructors to promote the use by students
of these strategies in online courses aim to improve the academic performance of their
students [18].
According to [19] learner success in an e-learning system can be explained by self-

4
regulation and learners' intention to continue using educational platforms, they also
show that learners' intention to continue using these educational platforms can be ex-
plained by learner satisfaction, and self-regulation can be explained by personal effort
and course flexibility, and although the following factors: perceived usefulness, social
interactions, system quality, course and information quality, course flexibility, and
diversity of assessments can improve learner satisfaction with educational platforms.
According to [20], parents (family causal factors), teachers (school causal factors),
and students (personal causal factors) can influence final performance. The combina-
tion of these factors influencing academic performance, however, varies from one
academic environment to another, from one group of students to another, and even
from one cultural setting to another.
Other factors play a role in online learning satisfaction and success that were all
related to learner characteristics and course design characteristics of e-learning envi-
ronments [21]. On the one hand, learner characteristics including self-regulation skills,
time management, online learning style, knowledge, one that demonstrates better
emotional intelligence (i.e. a better knowledge of his/her needs, self-regulation of
feelings), self-motivation, self-discipline, organization, planning, and self-assessment.
On the other hand, professors/instructors need to know the course design characteris-
tics of online learning environments that promote student success and satisfaction,
including time management, course alignment, and organization, integration of con-
tent with technology to facilitate engagement, instructor facilitation, instructor's com-
ments, prompt feedback which is a primary factor in online satisfaction, and the size
of the course which should not be large. Successful online learning also requires inter-
action between the learner, the instructor, the learners, and the technology.
The virtual learning environment effectiveness model of [22] posits that two ante-
cedents (design dimension and human dimension) determine the effectiveness of e-
learning systems. The human dimension concerns two human entities (the students
and the instructor) and their different attributes; and the design dimension includes
learning management systems (LMS), self-regulated learning (SRL) and learner con-
trol, the quality of course design, and the interaction between human entities.
Learning analytics provides opportunities for students to reflect on learning and
develop metacognitive skills. So in order to be successful in self-regulation, it is nec-
essary for students to understand their own cognitive process. To this end, linking
visualizations to learning goals can help learners and instructors assess whether the
goal has been achieved [23].
Interactions with the learning community members that includes learners and in-
structors, social presence, positive support, engagement, critical thinking, and overall
assessment results have a positive impact on the concept of knowledge and skills ac-
quired during the online learner's learning path that represents the backbone of the
online learner experience [24]. In addition, forums play an important role in collabora-
tive student learning, also allow students to interact. Students who participate most
actively in the discussion forum are those who succeed in the course [25]. Course
structure, class size, feedback, prior digital communication knowledge, interface char-
acteristics, content area experience, student roles and pedagogical tasks, differences in

5
student demographics and abilities, etc. are factors that can influence student partici-
pation in these online discussion forums [26]. Other research results affirm that all
students learn best when the instruction, resources, and learning environment are well-
matched with their strengths, interests, needs, and their level of knowledge [27], [28].
Hence, the conclusion that personalization of learning is one of the main axes that
must be taken into account if we want to see student outcomes improve.
Another aspect to take into account is the evaluation of learning. Students' learning
depends on how they are evaluated and with what instruments [29]. Thus, the teacher
assesses the student to identify the evolution through different levels of learning. On
the one hand, depending on the level reached, the instructor proposes actions and ma-
terial to improve the performance of the students [30] evaluations, videos, tests, con-
ferences, among others. Each student, on the other hand, learns at his/her own pace.
This requires personalizing the mechanisms used according to each student. Infor-
mation and communication technologies can help the teacher discover who is learning
and who is not motivated. They can suggest actions like when, who, and how to eval-
uate or what activities can be realized.
3 Proposed Model
In this section, we will describe our proposed robust model of e-learning environ-
ments that offer the personalization of learning to the specific skills and needs of each
learner in order to improve the learning experience of the students, whose goal is to
increase their success rate as well as reducing their dropout rate in these e-learning
systems. Fig 1 shows our proposed model. It is then a matter of personalizing the
learning objects, adapt teaching methods, helping the learner to use self-regulated
learning strategies, as well as the feedback and evaluations provided by the teacher,
that they will be personalized according to the learner's profile. In an e-learning sys-
tem, they can be applied as components, also linking the visualizations to the learning
goals in order to help learners and teachers to evaluate if the objective has been
achieved. This is a useful practice for teachers and especially for learners since it al-
lows the learner to be accompanied at any time and any place and tests his/her
knowledge and skills. Hence the system requires a dynamic combination between the
learner's demands (his/her interests, preferences, level of knowledge) and the possi-
bilities of personalization.
The Learner's need is to learn. Our objective is to help him/her learn, to become
autonomous, to be satisfied, and to succeed in his/her learning. In the e-learning sys-
tem, the learner visualizes the learning objects provided by the teacher which are per-
sonalized according to his/her profile by the e-learning system, he/she has to evaluate
his/her knowledge and level of understanding. Also, the learner has to be able to de-
fine his/her objectives, to make decisions in his/her program, to apply the right learn-
ing strategies which are cognitive strategies where the learner can take notes, summa-
rize, create mental associations, use images and audio documents, use the mother
tongue; metacognitive strategies are there to reinforce memorization and reflect on the
learning process by setting goals, reflecting on him/her way of working, having a

6
personal learning journal, self-evaluation; socio-affective strategies bring the learner
closer to his/her emotions and feelings by cooperating with peers, encouraging each
other, opening up to others.
The role of the Teacher is crucial. He/she has to design educational sequences,
evaluate the level of the learners, use the educational material provided... E-learning
doesn’t consist of simply letting learners navigate through a set of resources; it is a
matter for the teacher accompanying them in their learning process through the design
of educational activities integrated into a coherent scenario. The teacher's and the e-
learning system's roles are therefore also to guide the learners to identify the best
strategies, to help them learn and understand also to helping them to self-regulate.
The sub-components of the "Learner profile" component are as follows: history
of his/her navigation (his/her learning established on the basis of his/her last interac-
tions with the learning environment); his/her performance (this sub-component up-
dates information about the learner through the results of the suggested evaluations);
his/her preferences (based on his/her interaction with the learning environment, we
determine the language of teaching, types of learning objects and preferred types of
questions).
Fig. 1. Our Proposed Model of E-Learning System for Successful Education.
The "Evaluation" component aims to provide the learner with a personalized evalua-
tion based on the information provided in his/her profile (e.g. preferences, type of
questions, results obtained in the evaluations). It plays an essential role in how stu-
dents learn, how they are motivated to study, and how teachers instruct. While teach-
ers, students, and the online learning environment work to achieve the learning out-
comes, evaluation plays a critical role in providing useful information to guide teach-
ing, help students achieve the next steps, and verify progress and accomplishments.
Evaluation serves a variety of goals:
• Evaluation in the service of learning: evaluation informs teachers and the online
learning environment about what students understand and allows them to know
what learning objects to adjust and to plan and guide teaching while providing use-
0
5
10
15
20
25
30
35
40
45
50
0 5 10 15 20 25 30
Data A
Data B

7
ful feedback to students.
• Evaluation as learning: evaluation allows learners to become aware of how they
learn, to adjust and progress their learning by assuming increased responsibility for
it.
• Evaluation of learning: the information gathered from the evaluation allows stu-
dents, teachers, and the online learning environment to be informed about the
learning outcomes achieved at a specific time in order to highlight successes, plan
interventions, and keep promoting success.
The evaluation should be planned according to these goals. Evaluation in the service
of learning, evaluation as learning, and evaluation of learning each have a role to play
in supporting and enhancing students learning. In addition, the effective evaluation
does not apply the same evaluation strategy to all learners because their knowledge is
different. Some students should be evaluated on the entire learning content to evaluate
their overall knowledge; others only need to assess their current knowledge in a few
learning steps, which allows them to access the parts of the course that are most ap-
propriate for their level of knowledge. The aim is to orient the learner to the most
appropriate resources for his or her needs through a personalized evaluation. Based
on the results of the test, a personalized learning itinerary will be provided. The three
most popular types of evaluation are as follows:
• Pre-evaluation: Before they start learning, it is essential to know what type of stu-
dents it is addressed, situating their level of knowledge and preferences. A person-
alized program can then be created based on the data collected.
• Formative evaluation: used during the first attempt at learning. By keeping track of
students' progress and obtaining feedback to identify obstacles and individual dif-
ficulties to the diversity of students to provide individualized help and to adapt
"Teaching methods". Basically, three teaching methods enhance the student
learning experience: descriptive learning (reading, hearing), visual learning (pic-
tures, videos, and demonstration), and collaborative learning (participatory).
• Summative evaluation: aims to evaluate if the most important knowledge has been
acquired when the training is completed, in order to adjust the rest of his/her in-
structing according to the level achieved.
Also, providing learners with personalized "Feedback" on their performance is an
effective strategy for promoting learning, with congratulatory messages (e.g., if the
learner has successfully achieved his or her goal, a message appears saying "Well
done, I'm proud of you") and advisory messages (e.g., if the learner receives a low
grade, a message appears saying "Anyone can make mistakes, take extra time next
time. ").
We then focus on promoting students' use of "Self-Regulated Learning Strategies"
in an e-learning environment and on personalizing them according to their profile. The
model of [11] was the most frequently accepted and we will use it. As shown in Fig 2
of [11], who postulated that SRL occurs in three cyclical phases: forethought, perfor-
mance, and self-reflection [11], [31]. Each phase of self-regulated learning consists of
processes that self-regulated learners engage in (Fig 3 describes the fishbone diagrams
of each process), and each phase influences the processes of the next phase, and the
third, in turn, influences the first again. The fishbone diagram is a diagram that graph-
ically represents the causes leading to an effect, and can also be called a cause and
effect diagram [32].

8
Fig. 2. Phases and sub processes of self-regulation [33].
The Forethought Phase of self-regulated learning describes the processes by which
learners start to launch plans to complete a task or attain a goal (see Fig 3 (a)). The
Performance Phase describes the processes learners employ to accomplish a task or
goal (see Fig 3 (b)). In the Self-reflection Phase, learners reflect on their progress
toward the task or goal, or the results if they have completed the task (see Fig 3 (c)).
Fig. 3. Fishbone diagrams of the Forethought Phase (a), Performance Phase (b), and Self-
Reflection Phase (c) processes [33].
Since students do not necessarily develop SRLS when taking online courses, even
though these SRLS are of greater importance in online learning environments due to
their more autonomous nature, instructors should consider implementing these strat-
egies to help learners promote positive SRLS [18], but for instructors, it is difficult
to fully understand each learner's profile to help them use these strategies and to
(a (a)
(a)
(b)
(c)

9
personalize these SRLS according to each learner's profile. Therefore, we propose to
provide e-learning systems with specific strategies to encourage and help students to
use these effective SRLS, which will be personalized to their profiles. Some students
know how to launch plans, but some for example do not know how to manage their
time. Also, for example, some students want help (Help-Seeking) while others want
help to guide their learning. It is therefore the role of our proposition, to offer per-
sonalized self-regulation strategies to e-learning systems, to help them self-regulate.
Therefore, to succeed in self-regulation, students must understand their cognitive
process [23]. Using goal-oriented visualizations of activity tracking is an interesting
experience in analyzing student-centered learning through visualizations [34]. In this
case, we add a "Dashboard" component to the e-learning system to allow students to
reflect on their activity and compare it with their peers through dashboards. For this
aim, the collected information such as their learning performance will be displayed
in visualization to help them in their future decisions on task or goal completion.
In the next section, a description of the proposed approach is shown in the form of
a sequence diagram that shows the scenario behind the background of our model.
4 Scenario of the proposed model
In this section, we will describe the context of our research using the personalized
learning environment scenario.
Once identified, the teacher adds learning objects, evaluations, and feedback. One
identified as well, the learner navigates and consults educational resources. These
traces of the learner's interaction with the learning system are used by the adapter
component to better define the learner's preferences (teaching language, types of
learning objects, types of questions, etc.). The adapter's function is to personalize the
learning resources according to the learner's profile and to consult the traces, results,
and profiles of other learners in order to propose the best configuration to each new
learner. The adapter will also help the learner to self-regulate.
The learner must define his/her goal, if he does not do so the system asks him/her
to define it. For example, Yasmine is a student in computer engineering who would
like to learn the C language, the system sends Yasmine's objective, the resources
(learning objects, evaluations), and the feedback provided by the teacher to the adapter
to form a pre-evaluation on the chosen objective. After Yasmine answers the corre-
sponding questions and according to the results obtained (the questions that were not
answered correctly), the adapter depends on it to generate personalized feedback to
Yasmine, teaching methods adapted to her needs, and a program personalized to her
profile (preferences, performance).
She starts learning and to achieve her goal she starts using self-regulation strate-
gies, so the adapter will help her to use them aiming to improve her academic perfor-
mance. For example, she decides to ask for help every week on the parts she did not
understand well, and unfortunately at the end of the semester, Yasmine does not re-
ceive a good grade in the course. So she attributes the cause (i.e., causal attribution) to
the strategy used (i.e., seeking help did not help her achieve her goal). In the course
that follows, Yasmine will decide not to pursue this strategy.

10
Fig. 4. Personalized E-Learning system sequence diagram.

11
In order to successfully self-regulate, the system displays the collected infor-
mation, e.g. her learning performance, in a goal-oriented visualization so that Yasmine
can track her progress towards her goal. Thus, to ensure that Yasmine understands the
important concepts of the C language, questions will be researched by the adapter and
presented to constitute personalized formative evaluations on this lesson, estimating
her level of knowledge at each stage of the learning. The adapter should save Yas-
mine's progress and tracks in order to use them for future evaluation activities and
form personalized feedback according to her profile until she achieves her goal.
Finally, the adapter forms a personalized summative evaluation to Yasmine to af-
firm that she has succeeded in achieving her goal, that she has understood the im-
portant language C concepts, and give her personalized feedback, e.g. motivational
messages, advice, etc. For example, if she succeeded with a good grade the adapter
sends a message saying "Congratulations, it was hard but you did it", this is a motiva-
tional message. Figure 4 illustrates a sequence diagram, which shows this scenario
behind the background of this personalized e-learning system.
5 Conclusion and Future Work
In this article we have proposed a new model of online learning environment, help-
ing the learner to self-regulate and make his/her learning in the e-learning system
more accessible, easier, more personalized, more credible, and more desirable which
ultimately leads him/her to better success. Thus, we presented the main factors that
influence learners' success in their learning experiences that we included them in the
model in order to improve the learning experience and presented a description of the
proposed approach in the form of a sequence diagram that shows the scenario behind
the background of our model. For future studies, we will experimentally validate this
proposed model. Additionally, we suggest further study regarding learner-controlled
online learning, how, what, when, and where to learn, which may lead to self-
regulation skills and may be a factor in dropout rates of e-learning courses.
References
[1] N. Baudoin et al., “Le bien-être et la motivation des élèves en période de ( dé )
confinement Note de synthèse,” pp. 1–12, 2020, doi: 10.1111/bjep.12342.
[2] L. Bowman-Perrott, H. Davis, K. Vannest, L. Williams, R. Parker, and C. Greenwood,
“Academic benefits of peer tutoring: A meta-analytic review of single-case research,”
School Psychology Review, vol. 42, no. 1. pp. 39–55, Mar. 2013, doi:
10.1080/02796015.2013.12087490.
[3] Y. Lee and J. Choi, “A review of online course dropout research: Implications for
practice and future research,” pp. 593–618, 2011, doi: 10.1007/s11423-010-9177-y.
[4] S. B. Eom and N. J. Ashill, “A System ’ s View of E-Learning Success Model,” vol.
16, no. 1, pp. 42–76, 2018.
[5] R. Jahanbakhsh, “Learning Styles and Academic Achievement: a Case Study of
Iranian High School Girl’s Students,” Procedia - Soc. Behav. Sci., vol. 51, no. 1988,

12
pp. 1030–1034, 2012, doi: 10.1016/j.sbspro.2012.08.282.
[6] E. Kyndt, F. Dochy, K. Struyven, and E. Cascallar, “The direct and indirect effect of
motivation for learning on students’ approaches to learning through the perceptions of
workload and task complexity,” High. Educ. Res. Dev., vol. 30, no. 2, pp. 135–150,
2011, doi: 10.1080/07294360.2010.501329.
[7] C. Sorgenfrei and S. Smolnik, “The Effectiveness of E-Learning Systems : A Review
of the Empirical Literature on Learner Control,” vol. 14, no. 2, 2016.
[8] A. J. Martin, “Motivation and engagement: Conceptual, operational and empirical
clarity,” pp. 0–15, 2012.
[9] C. Kim, S. W. Park, J. Cozart, and H. Lee, “From Motivation to Engagement : The
Role of Effort Regulation of Virtual High School Students in Mathematics Courses,”
vol. 18, pp. 261–272, 2015.
[10] B. J. Zimmerman and D. H. Schunk, “Self-regulated learning and performance: An
introduction and an overview,” 2011.
[11] B. J. Zimmerman, “Motivational Sources and Outcomes of Self-Regulated Learning
and Performance,” no. 11237, 2011, doi: 10.4324/9780203839010.ch4.
[12] B. J. Zimmerman, “Investigating Self-Regulation and Motivation: Historical
Background, Methodological Developments, and Future Prospects,” vol. 45, no. 1, pp.
166–183, 2008, doi: 10.3102/0002831207312909.
[13] Dale H. Schunk, Judith R Meece, and Paul R. Pintrich, Motivation in Education:
Theory, Research, and Applications, 4th edition. 2014.
[14] Perry Nancy E. and Rahim Ahmed, “Studying self-regulated learning in classrooms ,”
2011.
[15] L. Barnard-Brak, V. O. Paton, and W. Y. Lan, “Self-regulation across time of first-
generation online learners,” Res. Learn. Technol., vol. 18, no. 1, Mar. 2010, doi:
10.3402/rlt.v18i1.10752.
[16] J. Ferla, M. Valcke, and G. Schuyten, “Judgments of self-perceived academic
competence and their differential impact on students’ achievement motivation,
learning approach, and academic performance,” Eur. J. Psychol. Educ., vol. 25, no. 4,
pp. 519–536, Dec. 2010, doi: 10.1007/s10212-010-0030-9.
[17] N. Dabbagh and A. Kitsantas, “Supporting Self-Regulation in Student-Centered Web-
Based Learning Environments,” Int. J. E-Learning, vol. 3, no. 1, pp. 40–47, 2004.
[18] J. B. Wandler and W. J. Imbriale, “Promoting Undergraduate Student Self-Regulation
in Online Learning Environments,” 2017, doi: 10.24059/olj.v21i2.881.
[19] Y. Safsouf, K. Mansouri, and F. Poirier, “An Analysis to Understand the Online
Learners’ Success in Public Higher Education in Morocco,” no. March, 2020, doi:
10.28945/4518.
[20] A. L. Diaz, “Personal, family, and academic factors affecting low achievement in
secondary school.,” undefined, 2003.
[21] H. Kauffman, “A review of predictive factors of student success in and satisfaction
with online learning,” Res. Learn. Technol., vol. 23, no. 1063519, pp. 1–13, 2015, doi:
10.3402/rlt.v23.26507.
[22] G. Piccoli, R. Ahmad, and B. Ives, “WEB-BASED VIRTUAL LEARNING AND A
RESEARCH FRAMEWORK ENVIRONMENTS : A PRELIMINARY
ASSESSMENT OF EFFECTIVENESS IN BASIC IT SKILLS TRAINING1,” vol. 25,

13
no. 4, pp. 401–426, 2001.
[23] E. Durall and B. Gros, “Learning Analytics as a Metacognitive Tool,” no. April, 2014,
doi: 10.5220/0004933203800384.
[24] R. Hammad, M. Odeh, and Z. Khan, “eLEM : A Novel e-Learner Experience Model,”
vol. 14, no. 4, pp. 586–597, 2017.
[25] C. Romero, M. López, J. Luna, and S. Ventura, “Predicting students ’ fi nal
performance from participation in on-line discussion forums,” Comput. Educ., vol. 68,
pp. 458–472, 2013, doi: 10.1016/j.compedu.2013.06.009.
[26] E. Yukselturk, “An investigation of factors affecting student participation level in an
online discussion forum,” Turkish Online J. Educ. Technol., vol. 9, no. 2, pp. 24–32,
2010.
[27] L. Prud, M. Leblanc, M. Paré, and P. Fillion, “Différencier d’abord auprès de tous les
élèves : un exemple en lecture,” 2015.
[28] H. Przesmycki, “La pédagogie différenciée,” pp. 2–3, 2004.
[29] I. D. García Carreño, “Hacía una evaluación integral con ePortafolio por evidencia y
bPortafolio,” 2012.
https://www.researchgate.net/publication/282133572_Hacia_una_evaluacion_integral
_con_ePortafolio_por_evidencia_y_bPortafolio (accessed Jun. 06, 2021).
[30] L. Leyva, Y. Garrido, J. L. L. Leyva, R. C. Varona, and R. H. R. Rodríguez,
“Reflexiones sobre la evaluación de la calidad del aprendizaje en la práctica
pedagógica en la escuela primaria,” undefined, 2007.
[31] B. J. Zimmerman, “Attaining self-regulation: A social cognitive perspective.,” pp. 13–
39, 2000.
[32] G. Watson, “The Legacy Of Ishikawa,” undefined, 2004.
[33] B. J. Zimmerman and M. Campillo, “Motivating Self-Regulated Problem Solvers,” pp.
233–262, 2003.
[34] J. L. Santos, S. Govaerts, K. Verbert, and E. Duval, “Goal-oriented visualizations of
activity tracking : a case study with engineering students,” pp. 143–152, 2012.