Rev. Cient. Sist. Inform. 4(2), e671, doi: 10.51252/rcsi.v4i2.671
Original article
Articulo original
Jul-Dec, 2024
https://revistas.unsm.edu.pe/index.php/rcsi
e-ISSN: 2709-992X
© The authors. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution,
and reproduction in any medium, provided the original work is properly cited.
Intelligent systems and their application in the evaluation of
university academic performance: A literature review in the
South American context
Sistemas inteligentes y su aplicación en la evaluación del desempeño académico
universitario: una revisión de la literatura en el contexto sudamericano
Magdalena Del-Águila-Castro 1*
1 Postgraduate School, Universidad César Vallejo, Tarapoto, Perú
Received: 12 Feb. 2024 | Accepted: 01 Jun. 2024 | Published: 10 Jul. 2024
Corresponding author*: magdaldac@gmail.com
How to cite this article: Del-Águila-Castro, M. (2024). Intelligent systems and their application in the evaluation of university academic
performance: A literature review in the South American context. Revista Científica de Sistemas e Informática, 4(2), e671.
https://doi.org/10.51252/rcsi.v4i2.671
ABSTRACT
The study aimed to analyze the impact of intelligent systems on improving academic performance and
personalized learning, through a review of 29 articles published between 2016 and 2024. It focused on the use
of artificial intelligence, machine learning, data mining, and intelligent tutoring systems in education. The results
showed that these technologies optimize educational assessment and improve academic performance.
Predictive models help identify students at risk of dropping out, enabling early interventions. Adaptive
architectures proved effective across various disciplines, and intelligent tutoring systems enhanced interaction
and feedback. Despite these advances, challenges remain in accessibility in resource-limited environments and
ethical concerns related to data privacy and algorithmic bias. The study highlights the need for an inclusive and
ethical approach to ensure these technologies transform education and benefit all students.
Keywords: artificial intelligence; educational equity; feedback; machine learning
RESUMEN
El estudio tuvo como objetivo analizar el impacto de los sistemas inteligentes en la mejora del rendimiento
académico y la personalización del aprendizaje, mediante una revisión de 29 artículos publicados entre 2016 y
2024. Se centró en el uso de la inteligencia artificial, el aprendizaje automático, la minería de datos y los sistemas
de tutoría inteligentes en la educación. Los resultados mostraron que estas tecnologías optimizan la evaluación
educativa y mejoran el rendimiento académico. Los modelos predictivos identifican a estudiantes en riesgo de
abandono escolar, facilitando intervenciones tempranas. Las arquitecturas adaptativas demostraron ser
efectivas en diversas disciplinas, y los sistemas de tutoría inteligentes mejoraron la interacción y la
retroalimentación. A pesar de estos avances, persisten desafíos en la accesibilidad en entornos con recursos
limitados, y preocupaciones éticas relacionadas con la privacidad de los datos y el sesgo algorítmico. El estudio
resalta la necesidad de un enfoque inclusivo y ético para garantizar que estas tecnologías transformen la
educación y beneficien a todos los estudiantes.
Palabras clave: aprendizaje automático; equidad educativa; inteligencia artificial; retroalimentación
Del-Águila-Castro, M.
2 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
1. INTRODUCTION
In recent decades, intelligent systems have profoundly transformed the field of educational evaluation,
enabling institutions to adopt innovative approaches to measure the performance of students and teachers
(Souza & Debs, 2024). Technologies such as artificial intelligence (AI), machine learning, and expert
systems have optimized the collection and analysis of educational data, offering more accurate and
personalized feedback (Delerna Rios & Levano Rodriguez, 2021; Wang et al., 2024). These advanced tools
are helping institutions improve educational quality and adapt to the growing demands of the digital age
(Zhai et al., 2021).
The evolution of intelligent systems in education has sparked increasing interest in research on their
impact on improving academic performance (García-Martínez et al., 2023). Researchers and educational
leaders have begun exploring how these technologies can complement or replace traditional evaluations,
which often focus on superficial metrics like grades or attendance (Ali et al., 2024). Instead, intelligent
systems can analyze large datasets, allowing for a deeper understanding of learning processes and early
detection of student performance issues (Kamalov et al., 2023).
Despite the growing adoption of these systems, their implementation poses several challenges, especially
in diverse educational settings. Institutions with varying levels of access to technology and resources face
difficulties in effectively integrating these systems (Mhlongo et al., 2023). Additionally, differences in
educational contexts, such as institutional size, government policies, and technological infrastructures,
affect the standardization of intelligent evaluation practices (Abulibdeh et al., 2024).
Another major challenge is the ethical debate surrounding the use of artificial intelligence in education.
Concerns about student data privacy and potential bias in the algorithms used for evaluation have raised
criticisms about large-scale implementation (Lim et al., 2023). Although these systems promise greater
equity by reducing human bias in assessments, the opacity of certain algorithms and the risk of
perpetuating pre-existing inequalities in the education system remain controversial aspects that need to
be addressed (Kamalov et al., 2023).
Studies on the application of intelligent systems in educational evaluation highlight both their benefits and
limitations. On the one hand, these technologies can facilitate more personalized and adaptive learning
environments, significantly improving student performance and engagement (Ali et al., 2024; Gligorea et
al., 2023). On the other hand, the lack of clear regulations and international standards hinders the
consistent implementation of these tools across different educational contexts, creating disparities in the
results obtained (Balasubramaniam et al., 2023).
In this context, the need for deeper research is evident. Current studies focus on exploring how these
systems can contribute to the development of more inclusive and equitable educational evaluations.
Advances in artificial intelligence and data analytics open new opportunities to identify learning patterns
and generate more precise educational interventions, but a critical approach is needed to ensure these
innovations are used ethically and effectively (Akinwalere & Ivanov, 2022; Malik et al., 2023).
The objective of this review is to provide a comprehensive overview of research conducted on the use of
intelligent systems in evaluating educational performance in the South American context. Through an
analysis of scientific literature indexed in databases such as Scopus, this study aims to identify key research
trends, knowledge gaps, and the opportunities these systems offer to improve educational quality in
various contexts. This research seeks to lay the groundwork for future studies and support the creation of
educational policies that promote broader and more effective use of intelligent technologies in evaluation.
Del-Águila-Castro, M.
3 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
2. MATERIALS AND METHODS
2.1. Research characterization
This study was conducted through a literature review to examine and analyze scientific research on the
application of intelligent systems in the evaluation of educational performance. A descriptive and
quantitative approach was used to analyze the scientific output, including academic articles and other
relevant indicators. The purpose was to identify and characterize the available research using data
obtained from specialized sources, providing a comprehensive overview of technological trends and
challenges encountered in this field.
2.2. Search procedures
In this study, the protocol proposed by Cronin et al. (2008) was followed, which includes the following
steps: (1) formulating the research question; (2) establishing inclusion and exclusion criteria; (3) locating
relevant articles; (4) evaluating the quality and relevance of the selected literature; and (5) analyzing and
synthesizing the findings. To define the selection criteria, the search was limited to materials published
between January 2013 and July 2024, focusing exclusively on articles in English and Spanish to ensure an
international perspective. The search process was carried out in a single stage, ensuring the thoroughness
of the review by strictly applying the defined criteria.
2.3. Search phase in Scopus
In the search phase, the following search term was used: ( "intelligent systems" OR "smart systems" OR
"automated systems" OR "autonomous systems" ) AND evaluation AND ( "educational performance" OR
"academic achievement" OR "learning outcomes" OR "student success" ) to identify articles related to the
use of intelligent systems in the evaluation of educational performance. The keywords included terms
covering both the technological aspects of the systems and their application in measuring academic
performance and learning outcomes. This search resulted in the identification of 5349 documents,
providing a solid foundation for further analysis of trends and challenges in the field.
Subsequently, in addition to the keywords, additional filters were applied to refine the results. Only
research articles (LIMIT-TO(DOCTYPE, "ar")) and articles from scientific journals (LIMIT-TO(SRCTYPE,
"j")), published between 2016 and 2024 (PUBYEAR > 2015 AND PUBYEAR < 2025), were included. The
search was limited to works affiliated with institutions in Latin American countries, specifically Brazil,
Colombia, Ecuador, Chile, Peru, Argentina, and Uruguay (LIMIT-TO(AFFILCOUNTRY, "Brazil") OR LIMIT-
TO(AFFILCOUNTRY, "Colombia") OR LIMIT-TO(AFFILCOUNTRY, "Ecuador") OR LIMIT-
TO(AFFILCOUNTRY, "Chile") OR LIMIT-TO(AFFILCOUNTRY, "Peru") OR LIMIT-TO(AFFILCOUNTRY,
"Argentina") OR LIMIT-TO(AFFILCOUNTRY, "Uruguay")). Additionally, the results were filtered to include
only articles within the area of Computer Science (LIMIT-TO(SUBJAREA, "COMP")) and written in English
or Spanish (LIMIT-TO(LANGUAGE, "English") OR LIMIT-TO(LANGUAGE, "Spanish")). After applying these
criteria, a total of 88 documents were obtained for analysis.
Despite applying specific search terms to restrict the results to the use of intelligent systems in the
evaluation of educational performance, the initial searches returned a significant number of unrelated
works. After reviewing the titles and abstracts, 29 articles were selected for the final review analysis. These
articles were considered the most relevant for analysis and provided a solid foundation for evaluating
trends and challenges in the use of intelligent technologies in education.
3. RESULTS AND DISCUSSION
Table 1 presents the articles selected for the analysis, detailing the code assigned to each article for easy
reference, along with the authors, year of publication, and title of each study and source journal.
Del-Águila-Castro, M.
4 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
Table 1.
Selected articles from Scopus databases
Code
Autors
Title
Journal
A1
(Mellado et al.,
2024)
Leveraging Gamification in ICT Education:
Examining Gender Differences and Learning
Outcomes in Programming Courses
Applied Sciences
(Switzerland)
A2
(Díaz &
Nussbaum,
2024)
Artificial intelligence for teaching and learning in
schools: The need for pedagogical intelligence
Computers and Education
A3
(Zapata-Medina
et al., 2024)
Improving the Automatic Detection of Dropout
Risk in Middle and High School Students: A
Comparative Study of Feature Selection
Techniques
Mathematics
A4
(Guanin-Fajardo
et al., 2024)
Predicting Academic Success of College Students
Using Machine Learning Techniques
Data
A5
(Vives et al.,
2024)
Prediction of Students' Academic Performance in
the Programming Fundamentals Course Using
Long Short-Term Memory Neural Networks
IEEE Access
A6
(Martinez-
Carrascal et al.,
2024)
Evaluation of Recommended Learning Paths Using
Process Mining and Log Skeletons:
Conceptualization and Insight into an Online
Mathematics Course
IEEE Transactions on
Learning Technologies
A7
(Theophilou et
al., 2024)
The effect of a group awareness tool in
synchronous online discussions: studying
participation, quality and balance
Behaviour and Information
Technology
A8
(Salazar et al.,
2023)
Sentiment analysis in learning resources
Journal of Computers in
Education
A9
(Huaman Llanos
et al., 2023)
Leveraging Text Mining for Analyzing Students'
Preferences in Computer Science and Language
Courses
Ingenierie des Systemes
d'Information
A10
(Álvarez et al.,
2023)
Proposed Model for the Alignment between
Curriculum Design and IT
RISTI - Revista Iberica de
Sistemas e Tecnologias de
Informacao
A11
(Garcia & Lemos,
2023)
The Gamification of E-learning Environments for
Learning Programming
International Journal on
Informatics Visualization
A12
(Jaramillo-
Morillo et al.,
2022)
Evaluating a learning analytics dashboard to
detect dishonest behaviours: A case study in small
private online courses with academic recognition
Journal of Computer Assisted
Learning
A13
(de Brito Lima et
al., 2022)
Learner behaviors associated with uses of
resources and learning pathways in blended
learning scenarios
Computers and Education
A14
(Flores et al.,
2022)
A New Methodological Framework for Project
Design to Analyse and Prevent Students from
Dropping Out of Higher Education
Electronics (Switzerland)
A15
(Mendoza et al.,
2022)
Assessment of Curriculum Design by Learning
Outcomes (LO)
Education Sciences
A16
(Rodríguez et al.,
2022)
Using scaffolded feedforward and peer feedback
to improve problem-based learning in large
classes
Computers and Education
A17
(Pincay-Ponce et
al., 2022)
Educational data mining: Incidence of
socioeconomic factors on school achievement
RISTI - Revista Iberica de
Sistemas e Tecnologias de
Informacao
A18
(Melillán &
Cravero, 2022)
Software engineering in the development of
technologies to support curriculum design: A
systematic mapping
RISTI - Revista Iberica de
Sistemas e Tecnologias de
Informacao
Del-Águila-Castro, M.
5 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
A19
(Vázquez-Cano
et al., 2021)
Chatbot to improve learning punctuation in
Spanish and to enhance open and flexible learning
environments
International Journal of
Educational Technology in
Higher Education
A20
(Gomez et al.,
2021)
Multi-agent systems for the management of
resources and activities in a smart classroom
IEEE Latin America
Transactions
A21
(Villegas-Ch et
al., 2021)
Analysis of the state of learning in university
students with the use of a hadoop framework
Future Internet
A22
(Freitas et al.,
2020)
IoT system for school dropout prediction using
machine learning techniques based on
socioeconomic data
Electronics (Switzerland)
A23
(Villegas-Ch et
al., 2020)
A business intelligence framework for analyzing
educational data
Sustainability (Switzerland)
A24
(Gomede et al.,
2020)
Use of deep multi-target prediction to identify
learning styles
Applied Sciences
(Switzerland)
A25
(Nieto et al.,
2019)
Supporting academic decision making at higher
educational institutions using machine learning-
based algorithms
Soft Computing
A26
(Luna-Urquizo,
2019)
Learning management system personalization
based on multi-attribute decision making
techniques and intuitionistic fuzzy numbers
International Journal of
Advanced Computer Science
and Applications
A27
(Alfaro et al.,
2019)
Using Project-based learning in a Hybrid e-
Learning system model
International Journal of
Advanced Computer Science
and Applications
A28
(Durães et al.,
2019)
Intelligent tutoring system to improve learning
outcomes
AI Communications
A29
(Carlotto &
Jaques, 2016)
The effects of animated pedagogical agents in an
English-as-a-foreign-language learning
environment
International Journal of
Human Computer Studies
Analysis of technological integration in education
In Table 2, the analysis of technological integration in education reveals how intelligent, automated, and
autonomous systems are transforming academic evaluation and personalized learning. Six studies (A2, A4,
A5, A9, A22, A25) highlight the use of artificial intelligence (AI) and machine learning to improve academic
performance and personalize teaching, while eight articles (A3, A6, A10, A14, A16, A22, A23, A26) focus on
automating evaluations, allowing for faster and more accurate analysis of student performance and
dropout prediction. Additionally, five studies (A1, A19, A20, A24, A28) explore the use of autonomous
systems, such as automated tutors, to facilitate adaptive teaching. The personalization of learning through
AI is addressed in seven studies (A2, A5, A9, A11, A13, A17, A26), which demonstrate how these systems
adjust educational experiences to individual needs, improving engagement and academic outcomes. Lastly,
seven studies (A3, A4, A5, A7, A14, A22, A25) show significant improvements in academic performance,
reduction in dropout rates, and optimization of learning pathways due to the integration of these systems.
Table 2.
Topics addressed in the research analyzed
Frequency
(Percentage)
Articles
6 (20.7%)
A2, A4, A5, A9, A22, A25
8 (27.6%)
A3, A6, A10, A14, A16, A22, A23, A26
5 (17.2%)
A1, A19, A20, A24, A28
7 (24.1%)
A2, A5, A9, A11, A13, A17, A26
Del-Águila-Castro, M.
6 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
7 (24.1%)
A3, A4, A5, A7, A14, A22, A25
6 (20.7%)
A2, A4, A5, A9, A22, A25
Analysis of methodological aspects
Table 3 presents the analysis of the methodological aspects of the selected studies, showing a diversity of
approaches used to evaluate the impact of intelligent systems in education. Most studies (A3, A4, A5, A14,
A22, A25) employ quantitative methods, using data analysis techniques based on machine learning and
artificial intelligence to predict academic performance and student dropout. Other studies (A2, A7, A19,
A20) apply mixed approaches that combine quantitative analysis with qualitative evaluations, allowing for
a more comprehensive analysis of student experiences and the impact of intelligent systems on
personalized learning. Finally, some articles (A6, A9, A17) use experimental methodologies, where systems
are implemented in controlled environments to measure their effectiveness in improving academic
performance and learning pathways. In summary, the studies show a trend toward integrating large-scale
educational data analysis through advanced AI techniques, focusing on personalization and academic
performance optimization.
Table 3.
Classification of documents according to methodological aspects
Frequency
(Percentage)
Articles
7 (24.1%)
A3, A4, A5, A14, A22, A25, A26
4 (13.8%)
A2, A7, A19, A20
3 (10.3%)
A6, A9, A17
5 (17.2%)
A4, A5, A6, A9, A22
6 (20.7%)
A2, A5, A6, A9, A11, A17
Analysis of theoretical elements
Table 4 presents the classification of the articles according to the theoretical frameworks used in the study
of methodologies, models, and architectures in the use of intelligent systems applied to education. A large
percentage of the articles focus on the use of machine learning models (24.1%) to predict academic
performance and student dropout. Other relevant topics include the development of intelligent tutoring
and multi-agent systems (17.2%) and the use of adaptive architectures and personalized learning (20.7%).
Studies on the analysis of learning pathways and process mining (13.8%) and the use of chatbots and
pedagogical agents (10.3%) to improve educational interaction are also highlighted. Additionally, the use
of data mining and analysis of large volumes of information (13.8%) is included to optimize academic
decision-making and student performance. This classification reflects the diversity of methodological and
architectural approaches in the analyzed studies, with a strong focus on using advanced technologies to
enhance education.
Table 4.
Classification of articles according to theoretical elements
Frequency
(Percentage)
Articles
7 (24.1%)
A3, A4, A5, A22, A24, A25, A14
5 (17.2%)
A19, A20, A28, A29, A7
6 (20.7%)
A2, A5, A9, A11, A17, A26
4 (13.8%)
A6, A13, A14, A22
3 (10.3%)
A19, A28, A29
Del-Águila-Castro, M.
7 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
Analysis of results
The inferential analysis of the 29 reviewed studies suggests that the implementation of intelligent systems
in education is consistently yielding results in terms of improving academic performance, personalizing
learning, and optimizing educational management. At a technical level, machine learning models have been
the most implemented for predicting academic outcomes, with a predominant focus on identifying students
at risk of dropout (A3, A4, A14). However, a key inference is that the success of these tools heavily depends
on the quality and quantity of educational data available. Current predictive systems, although accurate in
specific contexts, may present biases if not adequately integrated with qualitative variables such as
emotions and students' psychological well-being.
Regarding intelligent tutoring and multi-agent systems (A19, A20, A28), the results highlight significant
advances in learning personalization and these systems' ability to provide real-time feedback. However,
more research is needed on the effectiveness of these systems across different disciplines and educational
levels. Currently, most applications have focused on specific areas such as programming (A1, A5, A11),
raising the need to expand these systems to other fields of knowledge. The efficiency of intelligent tutors
can also be enhanced by integrating emerging technologies such as augmented reality or artificial
emotional intelligence, potentially improving student-system interaction.
A promising area of research is the combination of tutoring systems with learning pathway analysis (A6,
A13). Studies using process mining and large-scale educational data analysis have demonstrated how these
systems can optimize individualized learning paths. However, there is a lack of research on the long-term
impact of these technologies. Future research should focus on long-term studies to observe whether these
personalized pathways have a lasting effect on academic performance and knowledge retention.
Learning personalization through adaptive architectures and recommendation systems (A2, A5, A9) has
proven effective but presents a significant challenge related to scalability and student diversity. Future
research should address how these architectures can be adjusted to meet the needs of students with
different abilities, learning styles, and socioeconomic backgrounds. Moreover, implementing these
technologies in resource-limited institutions remains a challenge. Developing more accessible and cost-
effective solutions will be crucial to democratizing the use of these tools globally.
Regarding the interaction between students and intelligent systems through chatbots and pedagogical
agents (A19, A29), the results show an improvement in engagement and participation, but current studies
have been limited to basic feedback in areas such as punctuation or grammar. Future research should
explore how pedagogical agents can evolve to address complex questions and provide more robust support
in fields like mathematics and science. Additionally, the use of more advanced natural language processing
(NLP) technologies could enable these systems to handle deeper and more personalized interactions.
An important finding is the underutilization of data mining techniques and large-scale data analysis (A17,
A21, A23). Although these studies have shown that data mining can improve academic decision-making,
more research is needed on how to integrate these approaches with more advanced predictive models. For
example, combining data mining with neural network analysis or deep learning could offer a more complex
view of student behavior and performance, allowing for more precise and adaptive decision-making.
At the educational management level, the implementation of business intelligence frameworks (A23, A25)
has optimized curricular organization and academic planning. However, as these technologies continue to
develop, it will be necessary to integrate these systems with more complex educational platforms that
consider not only academic data but also metrics of student well-being, engagement, and satisfaction.
Future research should focus on developing algorithms that can synthesize this information to provide a
more holistic analysis of the educational environment.
Finally, a crucial area for future research is the ethics and social impact of intelligent systems in education.
Despite technological advances, challenges related to data privacy and potential bias in the algorithms used
Del-Águila-Castro, M.
8 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
for evaluation and prediction remain. Future studies should address how to mitigate these risks, ensuring
that technologies do not perpetuate existing inequalities and are inclusive for all students, regardless of
their background.
CONCLUSIONS
The study has shown that intelligent systems, such as machine learning and artificial intelligence,
significantly improve academic performance by personalizing learning and accurately predicting success
or dropout. Furthermore, the implementation of these systems optimizes educational assessment and
facilitates early interventions in at-risk students. However, challenges related to scalability and
accessibility have been identified, especially in resource-limited environments. To maximize their impact,
it is necessary to develop more inclusive technological solutions that are adaptable to diverse educational
contexts, expanding their applicability beyond technical disciplines.
On the other hand, tools such as data mining and intelligent tutoring systems have shown great potential
in improving academic decision-making and student-system interaction. Still, their integration into more
complex knowledge areas and their ability to offer deep feedback remain areas of future research. In
addition, it is essential to consider the ethical implications of these technologies, including data privacy and
potential biases in algorithms.
FINANCING
The author did not receive sponsorship to carry out this study-article.
CONFLICT OF INTEREST
There is no conflict of interest related to the subject matter of the work.
AUTHORSHIP CONTRIBUTION
Conceptualization, data curation, formal analysis, research, visualization, writing - original draft, writing -
proofreading and editing: Del-Águila-Castro
REFERENCES
Abulibdeh, A., Zaidan, E., & Abulibdeh, R. (2024). Navigating the confluence of artificial intelligence and
education for sustainable development in the era of industry 4.0: Challenges, opportunities, and
ethical dimensions. Journal of Cleaner Production, 437, 140527.
https://doi.org/10.1016/j.jclepro.2023.140527
Akinwalere, S. N., & Ivanov, V. (2022). Artificial Intelligence in Higher Education: Challenges and
Opportunities. Border Crossing, 12(1), 1–15. https://doi.org/10.33182/bc.v12i1.2015
Alfaro, L., Rivera, C., & Luna-Urquizo, J. (2019). Using Project-based learning in a Hybrid e-Learning
system model. International Journal of Advanced Computer Science and Applications, 10(10), 426–
436. https://doi.org/10.14569/ijacsa.2019.0101059
Ali, O., Murray, P. A., Momin, M., Dwivedi, Y. K., & Malik, T. (2024). The effects of artificial intelligence
applications in educational settings: Challenges and strategies. Technological Forecasting and Social
Change, 199, 123076. https://doi.org/10.1016/j.techfore.2023.123076
Álvarez, D., Melillán, A., Cravero, A., & Sepúlveda, S. (2023). Proposed Model for the Alignment between
Curriculum Design and IT | Propuesta de Modelo para el Alineamiento entre el Diseño Curricular y
las TI. RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao, 2023(E59), 531–543.
Balasubramaniam, N., Kauppinen, M., Rannisto, A., Hiekkanen, K., & Kujala, S. (2023). Transparency and
Del-Águila-Castro, M.
9 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
explainability of AI systems: From ethical guidelines to requirements. Information and Software
Technology, 159, 107197. https://doi.org/10.1016/j.infsof.2023.107197
Carlotto, T., & Jaques, P. A. (2016). The effects of animated pedagogical agents in an English-as-a-foreign-
language learning environment. International Journal of Human Computer Studies, 95, 15–26.
https://doi.org/10.1016/j.ijhcs.2016.06.001
Cronin, P., Ryan, F., & Coughlan, M. (2008). Undertaking a literature review: a step-by-step approach.
British Journal of Nursing, 17(1), 38–43. https://doi.org/10.12968/bjon.2008.17.1.28059
de Brito Lima, F., Lautert, S. L., & Gomes, A. S. (2022). Learner behaviors associated with uses of resources
and learning pathways in blended learning scenarios. Computers and Education, 191.
https://doi.org/10.1016/j.compedu.2022.104625
Delerna Rios, G. E., & Levano Rodriguez, D. (2021). Importancia de las tecnologías de información en el
fortalecimiento de competencias pedagógicas en tiempos de pandemia. Revista Científica de Sistemas
e Informática, 1(1), 69–78. https://doi.org/10.51252/RCSI.V1I1.104
Díaz, B., & Nussbaum, M. (2024). Artificial intelligence for teaching and learning in schools: The need for
pedagogical intelligence. Computers and Education, 217.
https://doi.org/10.1016/j.compedu.2024.105071
Durães, D., Toala, R., Gonçalves, F., & Novais, P. (2019). Intelligent tutoring system to improve learning
outcomes. AI Communications, 32(3), 161–174. https://doi.org/10.3233/AIC-190624
Flores, V., Heras, S., & Julián, V. (2022). A New Methodological Framework for Project Design to Analyse
and Prevent Students from Dropping Out of Higher Education. Electronics (Switzerland), 11(18).
https://doi.org/10.3390/electronics11182902
Freitas, F. A. D. S., Vasconcelos, F. F. X., Peixoto, S. A., Hassan, M. M., Ali Akber Dewan, M., de Albuquerque,
V. H. C., & Rebouças Filho, P. P. (2020). IoT system for school dropout prediction using machine
learning techniques based on socioeconomic data. Electronics (Switzerland), 9(10), 1–14.
https://doi.org/10.3390/electronics9101613
García-Martínez, I., Fernández-Batanero, J. M., Fernández-Cerero, J., & León, S. P. (2023). Analysing the
Impact of Artificial Intelligence and Computational Sciences on Student Performance: Systematic
Review and Meta-analysis. Journal of New Approaches in Educational Research, 12(1), 171–197.
https://doi.org/10.7821/naer.2023.1.1240
Garcia, C., & Lemos, N. (2023). The Gamification of E-learning Environments for Learning Programming.
International Journal on Informatics Visualization, 7(2), 455–462.
https://doi.org/10.30630/joiv.7.2.1602
Gligorea, I., Cioca, M., Oancea, R., Gorski, A.-T., Gorski, H., & Tudorache, P. (2023). Adaptive Learning Using
Artificial Intelligence in e-Learning: A Literature Review. Education Sciences, 13(12), 1216.
https://doi.org/10.3390/educsci13121216
Gomede, E., de Barros, R. M., & de Souza Mendes, L. (2020). Use of deep multi-target prediction to identify
learning styles. Applied Sciences (Switzerland), 10(5). https://doi.org/10.3390/app10051756
Gomez, A., Chamba Eras, L. A., & Aguilar, J. (2021). Multi-agent systems for the management of resources
and activities in a smart classroom. IEEE Latin America Transactions, 19(9), 1511–1519.
https://doi.org/10.1109/TLA.2021.9468444
Guanin-Fajardo, J. H., Guaña-Moya, J., & Casillas, J. (2024). Predicting Academic Success of College
Students Using Machine Learning Techniques. Data, 9(4). https://doi.org/10.3390/data9040060
Huaman Llanos, A. A., Huatangari, L. Q., Yalta Meza, J. R., & Monteza, A. H. (2023). Leveraging Text Mining
for Analyzing Students’ Preferences in Computer Science and Language Courses. Ingenierie Des
Systemes d’Information, 28(5), 1265–1273. https://doi.org/10.18280/isi.280515
Jaramillo-Morillo, D., Ruipérez-Valiente, J. A., Burbano Astaiza, C. P., Solarte, M., Ramirez-Gonzalez, G., &
Alexandron, G. (2022). Evaluating a learning analytics dashboard to detect dishonest behaviours: A
case study in small private online courses with academic recognition. Journal of Computer Assisted
Learning, 38(6), 1574–1588. https://doi.org/10.1111/jcal.12734
Del-Águila-Castro, M.
10 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
Kamalov, F., Santandreu Calonge, D., & Gurrib, I. (2023). New Era of Artificial Intelligence in Education:
Towards a Sustainable Multifaceted Revolution. Sustainability, 15(16), 12451.
https://doi.org/10.3390/su151612451
Lim, T., Gottipati, S., & Cheong, M. L. F. (2023). Ethical Considerations for Artificial Intelligence in
Educational Assessments. In Creative AI Tools and Ethical Implications in Teaching and Learning (pp.
32–79). https://doi.org/10.4018/979-8-3693-0205-7.ch003
Luna-Urquizo, J. (2019). Learning management system personalization based on multi-attribute decision
making techniques and intuitionistic fuzzy numbers. International Journal of Advanced Computer
Science and Applications, 10(11), 669–676. https://doi.org/10.14569/IJACSA.2019.0101188
Malik, A. R., Pratiwi, Y., Andajani, K., Numertayasa, I. W., Suharti, S., Darwis, A., & Marzuki. (2023).
Exploring Artificial Intelligence in Academic Essay: Higher Education Student’s Perspective.
International Journal of Educational Research Open, 5, 100296.
https://doi.org/10.1016/j.ijedro.2023.100296
Martinez-Carrascal, J. A., Munoz-Gama, J., & Sancho-Vinuesa, T. (2024). Evaluation of Recommended
Learning Paths Using Process Mining and Log Skeletons: Conceptualization and Insight into an
Online Mathematics Course. IEEE Transactions on Learning Technologies, 17, 555–568.
https://doi.org/10.1109/TLT.2023.3298035
Melillán, A., & Cravero, A. (2022). Software engineering in the development of technologies to support
curriculum design: A systematic mapping | Ingeniería de Software en el desarrollo de tecnologías
para el apoyo al diseño curricular: Un mapeo sistemático. RISTI - Revista Iberica de Sistemas e
Tecnologias de Informacao, 2022(E50), 322–334.
Mellado, R., Cubillos, C., Vicari, R. M., & Gasca-Hurtado, G. (2024). Leveraging Gamification in ICT
Education: Examining Gender Differences and Learning Outcomes in Programming Courses. Applied
Sciences (Switzerland), 14(17). https://doi.org/10.3390/app14177933
Mendoza, W., Ramírez, G. M., González, C., & Moreira, F. (2022). Assessment of Curriculum Design by
Learning Outcomes (LO). Education Sciences, 12(8). https://doi.org/10.3390/educsci12080541
Mhlongo, S., Mbatha, K., Ramatsetse, B., & Dlamini, R. (2023). Challenges, opportunities, and prospects of
adopting and using smart digital technologies in learning environments: An iterative review. Heliyon,
9(6), e16348. https://doi.org/10.1016/j.heliyon.2023.e16348
Nieto, Y., García-Díaz, V., Montenegro, C., & Crespo, R. G. (2019). Supporting academic decision making at
higher educational institutions using machine learning-based algorithms. Soft Computing, 23(12),
4145–4153. https://doi.org/10.1007/s00500-018-3064-6
Pincay-Ponce, J., Herrera-Tapia, J., Terranova-Ruiz, J., Cruz-Felipe, M., Sendón-Varela, J., & Fernández-
Capestany, L. (2022). Educational data mining: Incidence of socioeconomic factors on school
achievement | Minería de datos educativos: Incidencia de factores socioeconómicos en el
aprovechamiento escolar. RISTI - Revista Iberica de Sistemas e Tecnologias de Informacao,
2022(E49), 654–667.
Rodríguez, M. F., Nussbaum, M., Yunis, L., Reyes, T., Alvares, D., Joublan, J., & Navarrete, P. (2022). Using
scaffolded feedforward and peer feedback to improve problem-based learning in large classes.
Computers and Education, 182. https://doi.org/10.1016/j.compedu.2022.104446
Salazar, C., Montoya-Múnera, E., & Aguilar, J. (2023). Sentiment analysis in learning resources. Journal of
Computers in Education, 10(4), 637–662. https://doi.org/10.1007/s40692-022-00237-9
Souza, A. S. C. de, & Debs, L. (2024). Concepts, innovative technologies, learning approaches and trend
topics in education 4.0: A scoping literature review. Social Sciences & Humanities Open, 9, 100902.
https://doi.org/10.1016/j.ssaho.2024.100902
Theophilou, E., Sanchez-Reina, R., Hernandez-Leo, D., Odakura, V., Amarasinghe, I., & Lobo-Quintero, R.
(2024). The effect of a group awareness tool in synchronous online discussions: studying
participation, quality and balance. Behaviour and Information Technology, 43(6), 1149–1163.
https://doi.org/10.1080/0144929X.2023.2200543
Del-Águila-Castro, M.
11 Rev. Cient. Sist. Inform. 4(2): e671; (Jul-Dec, 2024). e-ISSN: 2709-992X
Vázquez-Cano, E., Mengual-Andrés, S., & López-Meneses, E. (2021). Chatbot to improve learning
punctuation in Spanish and to enhance open and flexible learning environments. International
Journal of Educational Technology in Higher Education, 18(1). https://doi.org/10.1186/s41239-021-
00269-8
Villegas-Ch, W., Palacios-Pacheco, X., & Luján-Mora, S. (2020). A business intelligence framework for
analyzing educational data. Sustainability (Switzerland), 12(14), 1–21.
https://doi.org/10.3390/su12145745
Villegas-Ch, W., Roman-Cañizares, M., Sánchez-Viteri, S., García-Ortiz, J., & Gaibor-Naranjo, W. (2021).
Analysis of the state of learning in university students with the use of a hadoop framework. Future
Internet, 13(6). https://doi.org/10.3390/fi13060140
Vives, L., Cabezas, I., Vives, J. C., Reyes, N. G., Aquino, J., Condor, J. B., & Altamirano, S. F. S. (2024).
Prediction of Students’ Academic Performance in the Programming Fundamentals Course Using
Long Short-Term Memory Neural Networks. IEEE Access, 12, 5882–5898.
https://doi.org/10.1109/ACCESS.2024.3350169
Wang, S., Wang, F., Zhu, Z., Wang, J., Tran, T., & Du, Z. (2024). Artificial intelligence in education: A
systematic literature review. Expert Systems with Applications, 252, 124167.
https://doi.org/10.1016/j.eswa.2024.124167
Zapata-Medina, D., Espinosa-Bedoya, A., & Jiménez-Builes, J. A. (2024). Improving the Automatic
Detection of Dropout Risk in Middle and High School Students: A Comparative Study of Feature
Selection Techniques. Mathematics, 12(12). https://doi.org/10.3390/math12121776
Zhai, X., Chu, X., Chai, C. S., Jong, M. S. Y., Istenic, A., Spector, M., Liu, J.-B., Yuan, J., & Li, Y. (2021). A Review
of Artificial Intelligence (AI) in Education from 2010 to 2020. Complexity, 2021(1).
https://doi.org/10.1155/2021/8812542