A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning
This 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 th...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10836232/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592951920820224 |
|---|---|
| author | Lauren Genith Isaza Dominguez Antonio Robles-Gomez Rafael Pastor-Vargas |
| author_facet | Lauren Genith Isaza Dominguez Antonio Robles-Gomez Rafael Pastor-Vargas |
| author_sort | Lauren Genith Isaza Dominguez |
| collection | DOAJ |
| description | This 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. |
| format | Article |
| id | doaj-art-b8fd1c9292f346dba6213f97f3cbe924 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-b8fd1c9292f346dba6213f97f3cbe9242025-01-21T00:00:57ZengIEEEIEEE Access2169-35362025-01-0113109781100210.1109/ACCESS.2025.352826310836232A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine LearningLauren Genith Isaza Dominguez0https://orcid.org/0000-0001-9726-2661Antonio Robles-Gomez1https://orcid.org/0000-0002-5181-0199Rafael Pastor-Vargas2https://orcid.org/0000-0002-4089-9538Programa de Doctorado en Tecnologías Industriales, Universidad Nacional de Educación a Distancia (UNED)—Escuela Internacional de Doctorado UNED (EIDUNED), Madrid, SpainEscuela Técnica Superior de Ingeniería Informática (ETSI Informática), Universidad Nacional de Educación a Distancia (UNED), Madrid, SpainEscuela Técnica Superior de Ingeniería Informática (ETSI Informática), Universidad Nacional de Educación a Distancia (UNED), Madrid, SpainThis 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.https://ieeexplore.ieee.org/document/10836232/Academic performanceengineering instructionensemble methodsFelder-Silverman learning styles model (FSLSM)machine learning (ML)predictive modeling |
| spellingShingle | Lauren Genith Isaza Dominguez Antonio Robles-Gomez Rafael Pastor-Vargas A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning IEEE Access Academic performance engineering instruction ensemble methods Felder-Silverman learning styles model (FSLSM) machine learning (ML) predictive modeling |
| title | A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning |
| title_full | A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning |
| title_fullStr | A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning |
| title_full_unstemmed | A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning |
| title_short | A Data-Driven Approach to Engineering Instruction: Exploring Learning Styles, Study Habits, and Machine Learning |
| title_sort | data driven approach to engineering instruction exploring learning styles study habits and machine learning |
| topic | Academic performance engineering instruction ensemble methods Felder-Silverman learning styles model (FSLSM) machine learning (ML) predictive modeling |
| url | https://ieeexplore.ieee.org/document/10836232/ |
| work_keys_str_mv | AT laurengenithisazadominguez adatadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning AT antonioroblesgomez adatadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning AT rafaelpastorvargas adatadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning AT laurengenithisazadominguez datadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning AT antonioroblesgomez datadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning AT rafaelpastorvargas datadrivenapproachtoengineeringinstructionexploringlearningstylesstudyhabitsandmachinelearning |