Adaptive Model for the Selection of Resources and Activities in a Virtual
Learning Environment
Yuranis Henriquez-Nunez
1,2 a
, Carlos Parra
2 b
, M
´
onica Brijaldo
2 c
and Angela Carrillo-Ramos
2 d
1
Universidad Tecnol
´
ogica de Bol
´
ıvar, Cartagena, Colombia
2
Pontificia Universidad Javeriana, Bogot
´
a D.C, Colombia
Keywords:
Education, VLS, Personalization, Adaptation, Learning Pathway, Resource, Activity.
Abstract:
This paper presents ALPY, an Adaptive System to support Personalized Education in Virtual Learning En-
vironments which favors the selection process of resources and activities for a learning pathway defined by
a teacher in a Virtual Learning System. This paper describes the proposed system’s architecture, the design
of the profiles in ALPY, and the visual prototype. It focuses on the adaptive model ALPY PLUS, and the
collection and processing of data or variables such as learning style, personality, and previous knowledge,
profiling students for suggested learning resources and activities. This model has been applied in an Systems
Engineering introductory course for students in the Tecnol
´
ogica de Bol
´
ıvar University.
1 INTRODUCTION
In the educational sector, multiple benefits are
achieved for participants using Information and
Communication Technologies (ICT) through Virtual
Learning Systems (VLS). According to authors such
as Hlib et al (Hlib et al., 2019), Foutsitzi et al (Fout-
sitzi and Caridakis, 2019), and UNESCO (UNESCO,
2017) when using a VLS, a large variety of resources
and tools are integrated to improve the performance
and practice during the learning process, achieving
a comprehensive inclusion of participants regardless
of space and time. However, several educational
challenges persist. Some of these challenges are re-
lated to the fact that each individual learns differ-
ently. Resources and activities are for the most part
not tailored to students’ individual educational ne-
cessities, and courses in general do not consider the
student’s profile,(Rosen et al., 2018), (Karataev and
Zadorozhny, 2017), (Iatrellis et al., 2020). There
are no tools that allow teachers to personalize re-
sources, (Karataev and Zadorozhny, 2017), (Khos-
ravi et al., 2020), (Kasinathan et al., 2017),(Meacham
et al., 2020) and the interfaces are not intuitive to
a
https://orcid.org/0000-0002-5139-2249
b
https://orcid.org/0000-0002-9695-3775
c
https://orcid.org/0000-0003-0075-5828
d
https://orcid.org/0000-0001-9086-5945
their participants, so the accessibility of learning re-
sources may also be lost (Karataev and Zadorozhny,
2017), (Iatrellis et al., 2020), (Alamri et al., 2018). In
order to tackle these challenges, this paper presents
ALPY: a technological solution that favors the edu-
cational process and offers, through VLS, a personal-
ized education adapted to the student. We emphasize
on the adaptive model (ALPY PLUS) used to select
resources and activities based on the characteristics
of the students and their context.
The remaining of this paper is organized as fol-
lows. Section 2 presents and discusses the related
works, highlighting their characteristics, advantages,
disadvantages, and ICT support in education for VLS.
Section 3 presents ALPY, describing the basic and
adaptive services, showing its architecture and main
design motivations in the context of VLS. Section 4
presents the case study detailing the processes and
development of ALPY Section 5 shows ALPY im-
plementation details. The results of this research are
analyzed in section 6, and finally, section 7, concludes
the paper and presents some pointers for future work.
2 RELATED WORK
This section presents a review of the works related to
personalized and adapted education in the VLS. We
256
Henriquez-Nunez, Y., Parra, C., Brijaldo, M. and Carrillo-Ramos, A.
Adaptive Model for the Selection of Resources and Activities in a Vir tual Learning Environment.
DOI: 10.5220/0011854900003470
In Proceedings of the 15th International Conference on Computer Supported Education (CSEDU 2023) - Volume 1, pages 256-263
ISBN: 978-989-758-641-5; ISSN: 2184-5026
Copyright
c
2023 by SCITEPRESS – Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)
Table 1: Comparison of related works, conventions:!Includes aspect, %Does not include aspect. RO(Rosen et al., 2018),
KA(Karataev and Zadorozhny, 2017), IA(Iatrellis et al., 2020), KH(Khosravi et al., 2020), WI(Williams et al., 2016),
KS(Kasinathan et al., 2017), AL(Alamri et al., 2018), ME(Meacham et al., 2020).
Criteria RO KA IA KH WI KS AL ME
Oriented to Students ! ! ! ! ! % ! %
Teachers % ! % ! % ! % !
Tutors % % % % % ! % %
Gamification activities No evidence ! ! % % ! ! ! !
Elements for customiza-
tion
No evidence ! ! % ! ! ! % !
Data for personalization Previous knowledge % % % ! ! ! % %
Past performances % ! % % % % % %
Learning outcomes ! % % % % % % %
Student profile % % % ! % ! % !
Student behavior ! % % % % % % %
Student interaction % % % % ! % % %
No evidence % % % % % % ! %
Adapted resources Contents ! ! ! % ! ! ! !
Activities % % ! % ! % % %
Pathway learning Implements in the VLS ! % ! % ! % % !
No evidence in the VLS % ! % ! % ! ! %
Platform Web ! ! ! ! % % ! !
Mobile % ! % % % % % %
Development environment % % % % ! % % %
No evidence % % % % % ! % %
consider works regarding ICT, supporting tools, and
basic strategies including adaptation, and ludic activ-
ities. There are some learner-oriented systems such
as ALOSI (Rosen et al., 2018), SALT (Karataev and
Zadorozhny, 2017), EDUC8 (Iatrellis et al., 2020),
RIPPLE (Khosravi et al., 2020), TOPOLOR (Alamri
et al., 2018), AXIS (Williams et al., 2016). There are
others VLS for teaching like: Kasinathan et al (Kasi-
nathan et al., 2017) that features Smart Sparrow tutor
system, Adaptive VLE (Meacham et al., 2020).
Table 1 details the strategies and tools used in
VLS to apply Personalized Education to these related
works. The symbol !specifies whether it is or not
a strategy or a tool, and the symbol %that describes
the absence of the aspect. It is important to notice
that most of the works are oriented towards students,
followed by teachers, and in few occasions tutors.
Regarding strategies, most works do not use gamifi-
cation and ludification elements. Additionally, most
works do not evidence changes in the presentation
and functionality of the visual interface. Concerning
the personalization strategy, most works highlight as-
pects such as previous knowledge, past performance,
student profile, student behavior in the course, and
student interaction in the system. The resource most
commonly adapted for the students is the educational
content followed by the activities. Although a study
plan or learning path is defined, most of these works
do not suggest any personalized contents and activi-
ties concerning the study plan. Lastly, these systems
are developed on platforms (web, development envi-
ronment, and mobile). Each of these related works
demonstrates the feasibility of creating a technology
solution to support personalized education. Neverthe-
less, few characteristics of the learner and their con-
text are considered in the works reviewed having only
ALOSI(Rosen et al., 2018) considering it as future
work. With this in mind, we believe that there is a
necessity for a system that includes basic individual
characteristics, preferences, context, teacher, course,
content, and activities to generate an adaptable and
personalized learning experience for each student in a
VLS.
3 ALPY
This section describes ALPY (an acronym for
Adapted Learning Pathway), an adaptive support sys-
tem for personalized education in virtual environ-
Adaptive Model for the Selection of Resources and Activities in a Virtual Learning Environment
257
Client
Web client
Mobile Client
Web browser
Mobile app
Server
Web server
Web application
Inference engine
Rule engine
Artificial
Intelligence
Student profile
Repository
Data persistence
Profiles
Teacher profile
Resource profile Activity profile
Pedagogical
model
Didactic
model
Learning
pathway
Context profile
Student profile
Course profile
ALPY PLUS ( Adaptation module)
Adapted Processes
Activity
Recommender
Resource
Recommender
3
4
4
5
1
2
Figure 1: ALPY Architecture.
ments. ALPY uses a learning pathway or study plan
as input and then it selects the educational contents
and activities, taking into account the individual char-
acteristics of the participant in the educational pro-
cess. To achieve this, ALPY contains three main com-
ponents. (see Figure 1).
• A database (DB) in which the information of the
participants in the VLS is stored through profiles.
These profiles contain the users’ individual char-
acteristics and the course’s particular characteris-
tics in the system.
• An adaptive module called ALPY PLUS used to
offer adjustable services in the VLS based on the
particular characteristics of the students. It is also
used to suggest educational resources to the VLS
teachers, so they can be facilitators in the partic-
ular learning process of their students through the
learning pathway.
• An inference engine based on machine learning
(AI) techniques, which recalculates rules in the
VLS based on established components and adapts
according to the information and behavior of the
participants.
3.1 ALPY Architecture
The proposed architecture for ALPY is detailed in
Figure 1 where the three components mentioned ear-
lier are depicted. It is worth mentioning that the paper
(Henriquez-Nunez et al., 2022) explained the initial
architecture of the ALPY model; however, through
the case studies, an update was developed and pre-
sented for this paper. Below we present the list of
services provided by ALPY:
• Generate a learning pathway defined by the
teacher (teacher user).
• Consult the learning pathway (student user).
• Consult the level of academic progress (teacher
and student user).
• Assess activities (student user).
• Evaluate activities (teacher user).
In accordance with the ALPY architecture Figure
1, the service’s invocation starts with the access of a
user from any client (1), either web or mobile, to the
VLS, thus requesting the VLS login service. Then,
the VLS responds with the interface adapted to the
type of client but without the services adapted to the
user (2). To enrich the service with adaptation char-
acteristics, ALPY PLUS, takes into account the user’s
data entered and data acquired in the database (such as
basic data, academic experience, learning style, likes
and interests of the student, and her/his environmental
context), analyzes the data to identify the student (3),
characterize her/him wiht the inference engine (4),
and subsequently group the data into a profile (5). At
the same time, the decision rules and AI modules de-
fined in the inference engine are activated. In addition
to this, 5 could request information from the reposi-
tory. Considering each of these steps in the interaction
path, with the defined architecture it is possible to of-
fer the mentioned services. Also, with these steps, it
is possible to offer new enriched services to the stu-
dents that allow them to continue favoring their learn-
ing, for example, by supporting monitoring according
CSEDU 2023 - 15th International Conference on Computer Supported Education
258
personality
user
state
course
extraversion
introversion
sensing
intuition
thinking
feeling
judging
perceptive
Student
user
name
state
background_knowledge_score
user
mathematics
critical_reading
english
learning_style
user
state
course
act_ref
sen_int
vis_vrb
seq_glo
course
user
course name
Figure 2: Class Diagram Student Profile.
to their peers who have completed one of the topics
of the course or keeping in mind the nearby location
of the students to manage a convenient schedule of
course advising.
This section will present the profiles proposed in
the ALPY architecture. According to the works ana-
lyzed in section 2, in order to allow the VLS to per-
sonalize the student’s learning process, a user profile
must be developed including basic data such as name,
identity document, and gender. In addition to the ba-
sic data, we must also consider the individual char-
acteristics of each user like learning domain, learning
style, likes, preferences, and interests, among other
data. The ALPY model integrates all these charac-
teristics inside its learner profile. For this adaptive
model, is crucial consider other profiles, such as those
of the course, teacher, content, activities, and context
or interaction of the system with the learner, which,
in contrast to the other profiles, include data related
to space-time, environment, social skills, and technol-
ogy. These characteristics will allow the learning sys-
tem to personalize and adapt the support resources,
improve the basic services, and include new adaptive
services, making the learning process more personal-
ized.
By detailing these profiles, it is possible to imple-
ment specific adaptive services and offer new ones.
For example, with the student profile, if there is data
about her/his learning style, it is possible to offer edu-
cational resources taylored to her/his style. Similarly,
having preferences data such as the way of studying
or study habits and frequency, we can provide the stu-
dent with monitoring services in the course. Data re-
lated to location or the use of the schedule, could de-
fine a tutoring service for the course. Finally, other
data could be technological like taking into account
the device, type of operating system, or resolution,
enable ALPY to offer adapted educational resources.
4 CASE STUDY
This section presents the ALPY prototype developed
for the introductory course of Computer Science at
Tecnol
´
ogica de Bol
´
ıvar University, hence implement-
ing student profiling to allows us to suggest personal-
ized content and activities for the student. For our ex-
perimentation we have a set of first-semester students
at the faculty of engineering who are taking the first-
semester fundamental subject in their area of study
using the MOODLE platform. In particular, we have
two groups that combined represent an audience of 73
people.
4.1 Data Capture
Once the profiles are built, the implementation is de-
veloped in the VLS, in this case, MOODLE (Moodle,
2022). The students are profiled according to Figure
2. The student profile contemplates not only the ba-
sic data including the user identification number and
full name in the VLS, but also, other data such as
basic knowledge, learning style, personality, and the
enrolled course. To obtain data like personality and
learning style, it was necessary to create two test-type
modules in the VLS, developed in languages includ-
ing HTML, CSS, and PHP and linked to MOODLE
libraries. The information about the student’s previ-
ous knowledge is currently shared by the university
through an institutional database that was queried to
obtain a comma separated value CSV file. By col-
lecting all the information, it is possible to visualize it
globally see Figure 3. It should be noted that the data
called “state” allows for a follow-up on whether or
not the student has developed the tests through which
enrichment information is obtained.
For the analysis of the students’ personality during
in the course, the Myers Briggs Test (MBTI) (Felder
Adaptive Model for the Selection of Resources and Activities in a Virtual Learning Environment
259
Figure 3: Data collected from students.
et al., 2002). was used, which measures personal pref-
erences or inclinations in the way of relating, pro-
cessing information, making decisions, or organizing
their lives, corresponding to four dichotomies, with
two extremes each one: Extraversion (E)/Introversion
(I), Sensing (S)/ Intuition (N), Thinking (T)/ Feeling
(F), Judging (J)/ Perceptive (P). When creating the
module in the VLS, we continued with the model that
proposes 72 situations, where the student must select
only those that reflect some aspect of her/his person-
ality. Each 9 of these 72 situations corresponds to an
extreme of the personality. Once the personality is de-
fined, the MBTI model presents how this type of per-
sonality thinks and behaves, suggesting activities and
processes that help her/his personal growth. Figure 3
shows that the letter with the highest score determines
the student’s personality inclination.
In order to identify the learning style study, we
use Felder and Soloman’s Test (Felder and Solo-
man, 1993), which proposes four bipolar categories
of learning styles, simplifying them as follows: Sen-
sitive(sen) / Intuitive(int), Visual(vis) / Verbal(vrb),
Active(act) / Reflective(ref) and Sequential(seq) /
Global(glo). When developing the module in the
VLS, the model was maintained and proposed 44 situ-
ations, 11 for each bipolar category, and with two pos-
sible answers called a or b. Once the learning style is
identified, a specific teaching technique is proposed to
meet the needs of most or all students in a given class.
Figure 3 shows the levels of preference and the letter
corresponding to only one of the bipolar categories in
the learning style, where 1 to 3 shows a low level, 5
to 7 is a moderate level, and 9 to 11 is a strong level.
Once the learning style is identified, the specific
teaching technique is proposed to address and thus
meet the needs of most or all students in any given
class.
Concerning the students’ prior knowledge, this
study takes into account as information the results of
the Colombian State exams in Secondary Education
called Saber 11 tests (Instituto Colombiano para la
Evaluaci
´
on de la Educaci
´
on - Portal ICFES, 2020).
These tests show the development of essential ca-
pabilities obtained by students in fundamental areas
such as Critical Reading, Mathematics, Citizenship
capabilities, Natural Sciences, and English; for this,
the state defines a performance scale classified into
four levels of performance that qualitatively describes
the skills and knowledge of the evaluated and quanti-
tatively has a score, where level 1 ( insufficient) starts
from 0 to 35, level 2 (minimum) from 36 to 50, level
3 (satisfactory) from 51 to 65 and level 4 (advanced)
has a score from 66 to 100. In this study, only the ar-
eas of Critical Reading, Mathematics and English are
considered at performance levels 3 and 4 as presented
in Figure 3, taking into account that most of our group
study focuses on these subjects.
Once the student’s information has been obtained,
that is to say, once we have complete information
about learning style, personality, and data from the
Colombian state exam, ALPY characterizes and inte-
grates the data into a set of profiles (see Figure 4). It is
important to note that ALPY has an initial profile, for
scenarios when information about learning style, per-
sonality, or data from the Colombian state exam are
not available for the suggestion of resources and ac-
tivities. This initial profile can be classified into four
cases with their respective suggestions:
• Case 1.There is no information about the learning
style, but there is information about their person-
ality and data from the state exams. According to
this information, a default activity is suggested.
• Case 2. There is no information about personal-
ity, but there is information about learning style
and data from the state exams. According to this
information, a default resource is suggested.
• Case 3. There is no information corresponding
to the data of the state exams; however, there is
information about learning style and personality.
According to this information, a default resource
and activities are suggested.
• Case 4. No information is available; nothing
is suggested, but general learning resources are
presented.
Complete information about the students will
make it much more effective to suggest resources and
activities.
According to the Figure 4, only one profile out of nine
possible is highlighted in blue. More specifically, if
CSEDU 2023 - 15th International Conference on Computer Supported Education
260
Figure 4: Defined ALPY profiles.
Introduction to Computer Science
Page 1
https://www.Alpy-Plus.com
LOGO
My CoursesMy Profile
Teacher
Welcome
My Progress
The University Engineering Systems engineering
Regional, national and
internacional context
The purpose of this course is to explore what systems engineering is at a global, national and regional level,
as well as to encourage reflection on the social responsibility associated with the exercise of the profession
with a social and historical perspective of its development at the regional level. The course seeks to promote
the successful introduction of new students to university life at the Technological University of Bolivar, by
promoting oral and written communication skills, teamwork, study techniques and management of software
and laboratory equipment typical of systems engineering
Support materials
Activities to develop
Forum "doubts and questions"
Activity Nº 1 - Self assessment quizzes
Read "Knowing the Jupyter tool"
Basic concepts maps
Course learning pathway
Student 3
Student 1
Student 2
Student 4
On-line
participants
Services
Tutoring schedule
Monitoring schedule
Calendar of activities and events
Notifications
Technical Support Center
Reports
Qualifications
Badges
Ludification activities
Test
active
thinking feeling
reflective
Learning style
Personality
Course download
Introduction to Computer Science
Welcome
My Progress
Services
On-line participants
My Profile
Services
-
-
My Courses
Test
Course
-
Support materials
Course learning pathway
Diagrams about doubt and questions
Jupyter Tool cards
Basic concepts crossword puzzles
Learning style
visual verbal
Personality
extraversion
introversion
+
+
+
+
Introduction to Computer Science
Welcome
My Profile
-
Test
-
Figure 5: Prototype according to profiles.
the student has an active learning style, thinking per-
sonality, and meets the established score at a satis-
factory or advanced level in the basic capabilities of
Critical Reading, English, and Mathematics, person-
alized learning resources are suggested.
In order to propose concrete examples with the data
of some students in the course, we have three profiles,
where the previously described profile relates to stu-
dents in the first group (group profile Nº1). For this
students, learning resources such as: Files, IMS Con-
tent Packages, books and URLs, will be suggested.
Likewise, the same learning resources will be sug-
gested for students in the group profile Nº2, where
they prefer a visual learning style; students in this pro-
file group have personality that tends to introversion
and meets the established score at a satisfactory or ad-
vanced level in the previous knowledge of the Saber
11 tests. For students in the profile group Nº3, who
have the sequential learning style, their personality is
judging and meets the established score at a satisfac-
tory or advanced level in the previous knowledge of
the Saber 11 tests. In this case, for the suggestion of
the learning resource, it is worth noticing that there
is the possibility of suggesting the same resources, as
in this case for the previous student group profiles,
but the defined personality of each group is the one
that introduces a change in the presentation of the
suggested resource. As mentioned before, students
in the group profile Nº1 consume the URL through
text, students in the group profile Nº2 uses graphics,
and student in the group profile Nº3 interacts with the
URL manually through sequences of steps, leading
the three students to the reflection of the same topic,
with the same resource, but in a different ways of
Adaptive Model for the Selection of Resources and Activities in a Virtual Learning Environment
261
study to match their personalities. Finally, regarding
the suggestions of learning activities for each student,
it could be the same activity, for instance, present-
ing a study material, but based on the personality of
each student, it will be suggested that students in the
first group are presented with the course material or-
ganized logically through concept maps, students in
the second group through crosswords, diagrams, puz-
zles, and students in the third group through a case
study with step by step instructions with a structure
with tasks, objectives, and milestones clearly defined.
5 ALPY PROTOTYPE
This section presents VLS with and without ALPY,
showing the visualization of the course for the defined
profiles.
5.1 VLS Without ALPY
The web and mobile interface is presented with the
primary services without adaptation, showing the es-
sential services of the course such as: consulting
the course plan, teacher and classmate contact infor-
mation, communicating by internal messaging with
classmates and teachers while being online in the
course, consulting course progress, activity, and grade
reports.
The figure 5 (left) illustrates a prototype of the
adapted course for the student using ALPY. The
VLS demonstrates the essential services mentioned
in the previous section, but addittionally, in green we
present the adaptive services. In this case, the Fig-
ure presents a web page prototype for the students
in the group profile Nº1. The activities, educational
resources are selected according to previous knowl-
edge, and we also include the active learning style,
and thinking personality in the visualization. In ad-
dition, this profile suggests contents including basic
conceptual maps, written documents, and activities
such as forums, among other ludic activities. Figure
5 (right) illustrates the same web page for the student
in the group profile Nº2. In this case, the course is
presented as a mobile client, the activities and edu-
cational resources are personalized according to the
previous basic knowledge, visual learning style, and
introversion personality. Additionally, the prototype
suggests visual learning content using crosswords for
the basic concepts, tool cards about the current topic,
and activities with written indications.
6 RESULTS
Once the concept proof was developed in the VLS
and considering the data analysis, the following re-
sults were obtained. Out of a total of 73 students who
participated by answering the learning style module,
it can be said that 16 students were classified as art of
the visual style, followed by 11 students that tend to
be sensitive, 7 sequential, 5 active, 4 present reflec-
tive, 2 global and 2 intuitive. It should be noted that
the group also presented the characteristic of not be-
ing defined in a single learning style; dichotomies and
trichotomies can be presented in the learning styles;
precisely 26 students had these characteristics.
When analyzing the personality module, those
with defined styles coincide with the grouping of pro-
files proposed in this study. As stated, a student who
has a visual style tends to have an introversion per-
sonality, and a verbal one tends to have an extrover-
sion personality; another example is a student who
has a sensitive learning style tends to have a sensitive
personality or if it is her/his intuitive style, her/his
personality is intuitive as well. Likewise, for those
not in a single learning style, the personality matches
the grouping of the profiles. For example, a student
with a visual-sequential dichotomy tended to have an
introversion-judging personality. However, the results
also suggested the possibility of new profiles in this
test, further strengthening this research.
7 CONCLUSIONS AND FUTURE
WORK
This paper presented the adaptive model of ALPY,
an Adaptive System to support personalized educa-
tion in Virtual Learning Environments. This paper
focused on presenting the process of profiling a stu-
dent in a VLS, obtaining and processing the necessary
student-specific data to suggest personalized learning
resources and activities for the student. This paper
developed several adaptive model tests in an intro-
ductory computer science course at Tecnol
´
ogica de
Bol
´
ıvar University. The tests and results demonstrate
an adequate student profiling and grouping of students
to suggest resources and activities in two steps, with-
out showing the conflict between the data of the de-
fined profiles. It also offers the possibility of provid-
ing new adaptive services according to their educa-
tional necessities and preferences. In other words, it
is possible to suggest a resource to support the student
by considering the student’s data, including her/his
learning style, personality, and previous knowledge
of Critical Reading, Mathematics, and English. The
CSEDU 2023 - 15th International Conference on Computer Supported Education
262
student’s personality can guide the personalization of
the type of resource and learning activity. It should
be noted that when developing these tests, the re-
sults suggested the possibility to define more than one
learning style; dichotomies and trichotomies have ap-
peared in our 73 student group subject to this study.
For future work, we plan to articulate an infer-
ence engine that establishes the decision rules to
further strengthen the adaptive services for suggest-
ing resources and activities and integrate into VLS
new evaluation mechanisms for teachers and feedback
mechanisms for students. We would like to involve
new enrichment data such as student capabilities fo-
cused on their careers, as well as new modules to mea-
sure student motivation, among others, to implement
new suggestions in VLS according to content and ac-
tivities.
ACKNOWLEDGEMENTS
The author Yuranis Henriquez Nu
˜
nez thanks to MIN-
CIENCIAS, for scholarship received in the “Convoca-
toria del Fondo de Ciencia, Tecnolog
´
ıa e Innovaci
´
on
del Sistema General de Regal
´
ıas para la conformaci
´
on
de una lista de proyectos elegibles para ser viabi-
lizados, priorizados y aprobados por el OCAD en el
marco del Programa de Becas de Excelencia Doctoral
del Bicentenario - Corte 1”. And Pontificia Univer-
sidad Javeriana and the Universidad Tecnol
´
ogica de
Bol
´
ıvar for the economic support received to pursue a
doctoral degree.
REFERENCES
Alamri, A., Rusby, H., Cristea, A. I., Kayama, M., Khan,
J., Shi, L., and Stewart, C. (2018). An Intuitive Au-
thoring System for a Personalised, Social, Gamified,
Visualisation-supporting e-learning System. In ACM
International Conference Proceeding Series, pages
57–61, New York, New York, USA. Association for
Computing Machinery.
Felder, R. M., Felder, G. N., and Dietz, E. J. (2002). The Ef-
fects of Personality Type on Engineering Student Per-
formance and Attitudes.
Felder, R. M. and Soloman, B. A. (1993). Learning Styles
AND Strategies. Strategies, pages 107–109.
Foutsitzi, S. and Caridakis, G. (2019). ICT in education:
Benefits, Challenges and New directions. Institute of
Electrical and Electronics Engineers Inc.
Henriquez-Nunez, Y., Parra, C., and Carrillo-Ramos, A.
(2022). ”ALPY PLUS - Adaptive Model Oriented to
Pathway Planning in Virtual Learning System,” pages
83-100.
Hlib, P., Zatonatska, T., and Liutyi, I. (2019). Utiliza-
tion of Information Technologies in Higher Education.
In 2019 IEEE International Conference on Advanced
Trends in Information Theory, ATIT 2019 - Proceed-
ings, pages 349–354. Institute of Electrical and Elec-
tronics Engineers Inc.
Iatrellis, O., Kameas, A., and Fitsilis, P. (2020). EDUC8
pathways: executing self-evolving and personalized
intra-organizational educational processes. Evolving
Systems, 11(2):227–240.
Instituto Colombiano para la Evaluaci
´
on de la Educaci
´
on -
Portal ICFES (2020). Acerca del examen Saber Pro.
Karataev, E. and Zadorozhny, V. (2017). Adaptive Social
Learning Based on Crowdsourcing. IEEE Transac-
tions on Learning Technologies, 10(2):128–139.
Kasinathan, V., Mustapha, A., and Medi, I. (2017). Adap-
tive learning system for higher learning. pages 960–
970. IEEE.
Khosravi, H., Sadiq, S., and Gasevic, D. (2020). Develop-
ment and adoption of an adaptive learning system re-
flections and lessons learned. pages 58–64, New York,
NY, USA. Association for Computing Machinery.
Meacham, S., Pech, V., and Nauck, D. (2020). Adap-
tiveVLE: An Integrated Framework for Personal-
ized Online Education Using MPS JetBrains Domain-
Specific Modeling Environment. IEEE Access,
8:184621–184632.
Moodle (2022). Moodle - Open-source learning platform
— Moodle.org.
Rosen, Y., Rushkin, I., Rubin, R., Munson, L., Ang, A.,
Weber, G., Lopez, G., and Tingley, D. (2018). The
effects of adaptive learning in a massive open online
course on learners’ skill development. pages 1–8, New
York, NY, USA. ACM.
UNESCO (2017). TIC, educaci
´
on y desarrollo social en
Am
´
erica Latina y el Caribe - UNESCO Biblioteca
Digital.
Williams, J. J., Kim, J., Rafferty, A., Maldonado, S., Gajos,
K. Z., Lasecki, W. S., and Heffernan, N. (2016).
AXIS. In Proceedings of the Third (2016) ACM Con-
ference on Learning @ Scale, pages 379–388, New
York, NY, USA. ACM.
Adaptive Model for the Selection of Resources and Activities in a Virtual Learning Environment
263