Publicación:
A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning

Vista sencilla de ítem
dc.contributor.authorIsaza Domínguez, Lauren Genith
dc.contributor.authorRobles Gómez, Antonio
dc.contributor.authorPastor Vargas, Rafael
dc.date.accessioned2025-02-21T10:40:15Z
dc.date.available2025-02-21T10:40:15Z
dc.date.issued2025-01-10
dc.descriptionEsta es la versión aceptada del artículo. La versión registrada fue publicada por primera vez en IEEE Access, vol. 13, pp. 10978-11002, 2025, está disponible en línea en el sitio web del editor: https://doi.org/10.1109/ACCESS.2025.3528263. This is the accepted version of the article. The registered version was first published in IEEE Access, vol. 13, pp. 10978–11002, 2025, and is available online at the publisher's website: https://doi.org/10.1109/ACCESS.2025.3528263.
dc.description.abstractThis study examined the impact of learning style and study habit alignment on the academic success of engineering students. Over a 16-week semester, 72 students from Process Engineering and Electronic Engineering programs at the Universidad de Los Llanos participated in this study. They completed the Learning Styles Index questionnaire on the first day of class, and each week, teaching methods and class activities were aligned with one of the four learning dimensions of the Felder-Silverman Learning Styles Model. Lesson 1 focused on one side of a learning dimension, lesson 2 on the opposite side, and the tutorial session incorporated both. Quizzes and engagement surveys assessed short-term academic performance, whereas midterm and final exam results measured long-term performance. Paired t-tests, Cohen’s effect size, and two-way ANOVA showed that aligning teaching methods with learning styles improved students’short-term exam scores and engagement. However, multiple regression analysis indicated that study habits (specifically time spent studying, frequency, and scores on a custom-developed study quality survey) were much stronger predictors of midterm and final exam performance. Several machine learning models, including Random Forest and Voting Ensemble, were tested to predict academic performance using study behavior data. Voting Ensemble was found to be the strongest model, explaining 83% of the variance in final exam scores, with a mean absolute error of 3.18. Our findings suggest that, while learning style alignment improves short-term engagement and comprehension, effective study habits and time management play a more important role in long-term academic success.en
dc.description.versionversión final
dc.identifier.citationL. Genith Isaza Domínguez, A. Robles-Gómez and R. Pastor-Vargas, "A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning," in IEEE Access, vol. 13, pp. 10978-11002, 2025, doi: https://doi.org/10.1109/ACCESS.2025.3528263
dc.identifier.doihttps://doi.org/10.1109/ACCESS.2025.3528263
dc.identifier.issn2169-3536
dc.identifier.urihttps://hdl.handle.net/20.500.14468/25956
dc.journal.titleIEEE Access
dc.journal.volume13
dc.language.isoen
dc.page.final11002
dc.page.initial10978
dc.publisherIEEE Xplore
dc.relation.centerFacultades y escuelas::E.T.S. de Ingeniería Informática
dc.relation.departmentSistemas de Comunicación y Control
dc.rightsinfo:eu-repo/semantics/openAccess
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/deed.es
dc.subject12 Matemáticas::1203 Ciencia de los ordenadores ::1203.17 Informática
dc.subject33 Ciencias Tecnológicas
dc.titleA Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learningen
dc.typeartículoes
dc.typejournal articleen
dspace.entity.typePublication
relation.isAuthorOfPublication17556659-f434-4220-841d-aac35f492e62
relation.isAuthorOfPublicationf93103de-336d-47ac-886b-e2cbd425ed87
relation.isAuthorOfPublication.latestForDiscovery17556659-f434-4220-841d-aac35f492e62
Archivos
Bloque original
Mostrando 1 - 1 de 1
Miniatura
Nombre:
RoblesGomez_Antonio_AData-driven_Approach_to.pdf
Tamaño:
1.01 MB
Formato:
Adobe Portable Document Format
Descargar
Bloque de licencias
Mostrando 1 - 1 de 1
No hay miniatura disponible
Nombre:
license.txt
Tamaño:
3.62 KB
Formato:
Item-specific license agreed to upon submission
Descripción:
Descargar
Colecciones
Artículos y papers