Abstract

Machine learning algorithms have been widely used for predicting learning styles in personalized e-learning systems. This paper evaluates effectiveness of a multi-level model using K-Means and Decision Trees algorithms to cluster learners into groups based on their characteristics and classify learners into the learning style dimensions of the Felder-Silverman learning styles model (FSLSM). Learner interaction data extracted from a Moodle Learning Management System (LMS) was pre-processed and used as input for K-Means clustering to group learners according to behavioural similarities. The resulting clusters were used to train and test a Decision Tree classifier that labelled each learner’s preferred learning style based on the FSLSM. The model was evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score. Evaluation results show that the proposed model achieved a 95% overall accuracy, with an emphasis on correctly identifying the learning style category across FSLSM dimensions, demonstrating the strong predictive performance of the proposed multi-level model in supporting automated learning style prediction.

References

• L. Zhong, “A systematic review of personalized learning in higher education: learning content structure, learning materials sequence, and learning readiness support,” Interactive Learning Environments, pp. 1-21, 2022.
• O. S. Adewale, O. C. Agbonifo and O. Lauretta, “Development of a myers-briggs type indicator based personalised e-Learning system,” International Journal of Computer (IJC), vol. 35, no. 1, pp. 101–125, 2019.
• R. M. Felder and L. K. Silverman, “Learning and teaching styles in engineering education,” Engineering education, vol. 78, no. 7, pp. 674–681, 1988.
• I. B. Myers, Gifts Differing: Understanding Personality Type. Palo Alto, CA, USA: Davies-Black Publishing, 1995.
• D. A. Kolb, Experience as the Source of Learning and Development. Upper Saddle River, NJ, USA: Prentice Hall, 1984.
• N. Fleming and D. Baume, “Learning Styles Again: VARKing up the right tree!,” Educational developments, vol. 7, no. 4, p. 4, 2006.
• L. X. Li and S. S. Abdul Rahman, “Students' learning style detection using tree augmented naive Bayes,” Royal Society open science, vol. 5, no. 7, p. 172108, 2018.
• F. Amastini, D. K. Sekarhati and M. Puspitasari, “Advancing Adaptive and Personalized E-Learning Systems: A Systematic Literature Review.,” Advance Sustainable Science Engineering and Technology, vol. 7, no. 2, pp. 0250209–0250209, 2025.
• P. Petchboonmee, D. Phonak and M. Tiantong, “A Comparative data mining technique for David Kolb's experiential learning style classification,” International Journal of Information and Education Technology, vol. 5, no. 9, p. 672, 2015.
• S. Garugu, V. B. Sri, E. Shravani, and B. Karthik, “Intelligent tutoring systems,” in A Comprehensive Guide to Personalized Learning, 2025Spector, A. Z. 1989.
• H. J. Cha, Y. S. Kim, S. H. Park, T. B. Yoon, Y. M. Jung and J. H. Lee, “Learning styles diagnosis based on user interface behaviors for the customization of learning interfaces in an intelligent tutoring system,” in Proc. 8th International Conference, Intelligent Tutoring Systems (ITS), pp. 513-524, 2006.
• S. Shi, S. Zhang, J. Hao, K. Chen and J. Wang, “MOOC Dropout Prediction Based on Bayesian Network,” in Proc. Machine Learning for Cyber Security: 4th International Conference, (ML4CS 2022), pp. 520–532, 2023.
• H. Zhang, T. Huang, S. Liu, H. Yin, J. Li, H. Yang and Y. Xia, “A learning style classification approach based on deep belief network for large-scale online education,” Journal of cloud computing, vol. 9, pp. 1–17, 2020.
• S. T. Sianturi and U. L. Yuhana, “Student behaviour analysis to detect learning styles using decision tree, naïve Bayes, and k-nearest neighbor method in Moodle learning management system,” IPTEK The Journal for Technology and Science, vol. 33, no. 2, pp. 94–104, 2022.
• S. Rami, S. Bennani and M. K. Idrissi, “Towards a new framework of automatic detection of learning style based on FSLM,” in Proc. Advanced Intelligent Systems for Sustainable Development (AI2SD’2020), vol. I, pp. 315–325, 2022.
• O. C. Agbonifo, O. S. Adewale and B. K. Alese, “Design of a neurofuzzy-based model for active and collaborative online learning,” International Journal of Education and Research, vol. 1, no. 10, pp. 1–22, 2013.
• S. Amin, M. I. Uddin, W. K. Mashwani, A. A. Alarood, A. Alzahrani and A. O. Alzahrani, “Developing a personalized e-learning and MOOC recommender system in IoT-enabled smart education,” IEEE Access, vol. 11, pp. 136437–136455, 2024.
• I. Azzi, J. Adil, A. Radouane, A. Yahyaouy and H. Tairi, “A robust classification to predict learning styles in adaptive e-learning systems,” Education and Information Technologies, pp. 1-12, 2019.
• G. P. B. Castro, A. Chiappe, D. F. B. Rodríguez, and F. G. Sepulveda, “Harnessing AI for Education 4.0: Drivers of personalized learning,” Electronic Journal of e-Learning, vol. 22, no. 5, pp. 1–14, 2024.
• E. Dalton, “Learn Moodle August 2016” anonymized data set, Moodle Pty Ltd., Feb. 15, 2017. [Online]. Available:https://research.moodle.org/files/anonymiseddatasetreadme.pdf. [Accessed: Mar. 12, 2024].
• B. K. Alese and A. O. Adetunmbi, “A machine learning approach for information system security,” International Journal of Computer Science and Information Security (IJCSIS), vol. 16, no. 12, 2018.
• I. Karagiannis and M. Satratzemi, “An adaptive mechanism for Moodle based on automatic detection of learning styles,” Education and Information Technologies, vol. 23, no. 3, pp. 1331–1357, 2018.