International Journal of Modern Education and Computer Science (IJMECS)
IJMECS Vol. 18, No. 3, 8 Jun. 2026
Cover page and Table of Contents: PDF (size: 870KB)
DistilBERT-based Text Classification for Learning Style Identification Based on the Felder-Silverman Model
PDF (870KB), PP.135-151
Views: 0 Downloads: 0
Author(s)
Index Terms
Learning Style Identification, Felder-Silverman Learning Style Model, Transformer-Based Text Classification, DistilBERT, Deterministic Questionnaire Modeling
Abstract
Identifying students’ learning styles is an important step in supporting adaptive and personalized learning environments, particularly in higher education contexts. This study investigates the use of a transformer-based language model, DistilBERT, for automated learning style identification based on the Felder–Silverman Learning Style Model (FSLSM). Binary responses from the 44-item Index of Learning Styles (ILS) questionnaire were systematically transformed into descriptive textual representations, preserving the underlying FSLSM decision logic while enabling semantic modeling. Separate DistilBERT classifiers were fine-tuned for the four FSLSM dimensions—Active/Reflective, Sensing/Intuitive, Visual/Verbal, and Sequential/Global. Model training was conducted using three epochs within a stratified five-fold cross-validation framework, with the primary objective of assessing optimization stability and representational consistency rather than predictive superiority. Across all dimensions, training loss decreased monotonically, with the most substantial reductions occurring between the first and second epochs, indicating rapid adaptation of pre-trained representations to the structured learning style descriptions. Differences in convergence behavior across dimensions were observed, reflecting variation in class distributions and response patterns. Near-perfect classification metrics were obtained across multiple folds; however, these results are interpreted as evidence of deterministic consistency between the textual inputs and FSLSM-derived labels rather than independent generalization performance. To examine alignment with human judgment, model predictions were further compared with expert assessments conducted independently using standard FSLSM interpretation guidelines. The resulting Cohen’s Kappa coefficient of 1.0 indicates perfect agreement, confirming that the model faithfully reproduces expert-consistent FSLSM categorizations under controlled conditions. Overall, the findings demonstrate that transformer-based models can reliably encode and recover rule-based learning style constructs from descriptive questionnaire data, supporting their use as computational tools for scalable, consistent learning style analysis, while acknowledging the task's deterministic and framework-dependent nature.
Cite This Paper
Nesi Syafitri, Suzani Mohamad Samuri, Yudhi Arta, "DistilBERT-based Text Classification for Learning Style Identification Based on the Felder-Silverman Model", International Journal of Modern Education and Computer Science(IJMECS), Vol.18, No.3, pp. 135-151, 2026. DOI:10.5815/ijmecs.2026.03.09
Reference
[1]J. W. Keefe, Student_Learning_Styles. National Association of Secondary School Principals, 1979.
[2]R. M. Felder and L. K. Silverman, “Learning and Teaching Styles in Engineering Education.,” 1988. [Online]. Available: https://api.semanticscholar.org/CorpusID:140475379
[3]F. Demir, C. Bruce-Kotey, and F. Alenezi, “User Experience Matters: Does One size Fit all? Evaluation of Learning Management Systems,” Technol. Knowl. Learn., vol. 27, no. 1, pp. 49–67, Mar. 2022, doi: 10.1007/s10758-021-09518-1.
[4]A. Lestari, A. Lawi, S. A. Thamrin, and N. Hidayat, “Automated Detection of Learning Styles using Online Activities and Model Indicators,” Int. J. Adv. Comput. Sci. Appl., vol. 15, no. 6, 2024, doi: 10.14569/IJACSA.2024.0150661.
[5]J. Bernard, T.-W. Chang, E. Popescu, and S. Graf, “Learning style Identifier: Improving the precision of learning style identification through computational intelligence algorithms,” Expert Syst. Appl., vol. 75, pp. 94–108, Jun. 2017, doi: 10.1016/j.eswa.2017.01.021.
[6]M. S. Hasibuan, R. A. Aziz, D. A. Dewi, T. B. Kurniawan, and N. A. Syafira, “Recommendation Model for Learning Material Using the Felder Silverman Learning Style Approach,” HighTech Innov. J., vol. 4, no. 4, pp. 811–820, Dec. 2023, doi: 10.28991/HIJ-2023-04-04-010.
[7]S. G. Essa, T. Celik, and N. E. Human-Hendricks, “Personalized Adaptive Learning Technologies Based on Machine Learning Techniques to Identify Learning Styles: A Systematic Literature Review,” IEEE Access, vol. 11, pp. 48392–48409, 2023, doi: 10.1109/ACCESS.2023.3276439.
[8]C. Waladi, M. Khaldi, and M. Lamarti Sefian, “Machine Learning Approach for an Adaptive E-Learning System Based on Kolb Learning Styles,” Int. J. Emerg. Technol. Learn., vol. 18, no. 12, pp. 4–15, 2023, doi: 10.3991/ijet.v18i12.39327.
[9]Z. Mehenaoui, Y. Lafifi, and L. Zemmouri, “Learning Behavior Analysis to Identify Learner’s Learning Style based on Machine Learning Techniques,” JUCS - J. Univers. Comput. Sci., vol. 28, no. 11, pp. 1193–1220, Nov. 2022, doi: 10.3897/jucs.81518.
[10]A. M. Altamimi, M. Azzeh, and M. Albashayreh, “Predicting students’ learning styles using regression techniques,” Indones. J. Electr. Eng. Comput. Sci., vol. 25, no. 2, pp. 1177–1185, Feb. 2022, doi: 10.11591/ijeecs.v25.i2.pp1177-1185.
[11]A. Ezzaim, A. Dahbi, A. Aqqal, and A. Haidine, “AI-based learning style detection in adaptive learning systems: a systematic literature review,” J. Comput. Educ., Jun. 2024, doi: 10.1007/s40692-024-00328-9.
[12]Y. Wei, Y. Liu, C. Li, J. Cheng, R. Song, and X. Chen, “TC-Net: A Transformer Capsule Network for EEG-based emotion recognition,” Comput. Biol. Med., vol. 152, p. 106463, Jan. 2023, doi: 10.1016/j.compbiomed.2022.106463.
[13]A. Das, O. Sharif, M. M. Hoque, and I. H. Sarker, “Emotion Classification in a Resource Constrained Language Using Transformer-based Approach,” in Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Student Research Workshop, 2021, pp. 150–158. doi: 10.18653/v1/2021.naacl-srw.19.
[14]X. Zhang, C. Li, W. Chen, J. Zheng, and F. Li, “Optimizing depression detection in clinical doctor-patient interviews using a multi-instance learning framework,” Sci. Rep., vol. 15, no. 1, p. 6637, Feb. 2025, doi: 10.1038/s41598-025-90117-w.
[15]M. M. Hossain, M. S. Hossain, M. F. Mridha, M. Safran, and S. Alfarhood, “Multi task opinion enhanced hybrid BERT model for mental health analysis,” Sci. Rep., vol. 15, no. 1, p. 3332, Jan. 2025, doi: 10.1038/s41598-025-86124-6.
[16]N. D. Fleming and C. Mills, “Not Another Inventory, Rather a Catalyst for Reflection,” To Improv. Acad., vol. 11, no. 1, pp. 137–155, Jun. 1992, doi: 10.1002/j.2334-4822.1992.tb00213.x.
[17]D. A. Kolb, “Experiential Learning: Experience as the Source of Learning and Development,” 1983. [Online]. Available: https://api.semanticscholar.org/CorpusID:146755699
[18]P. Honey and A. Mumford, Style of Learning. Gower Handb. Manag. Dev., 1994.
[19]P. Honey and A. Mumford, “The_Learning_Styles_Helper_s_Guide,” 2000.
[20]M. S. Hasibuan and R. A. Aziz, “Detection of Learning Styles with Prior Knowledge Data Using The SVM, K-NN and Naïve Bayes Algorithms,” J. INFOTEL, vol. 14, no. 3, pp. 209–213, Aug. 2022, doi: 10.20895/infotel.v14i3.788.
[21]I. Azzi, A. Radouane, L. Laaouina, A. Jeghal, A. Yahyaouy, and H. Tairi, “Fuzzy Classification Approach to Select Learning Objects Based on Learning Styles in Intelligent E-Learning Systems,” Informatics, vol. 11, no. 2, p. 29, May 2024, doi: 10.3390/informatics11020029.
[22]B. Muhammad et al., “A Fuzzy C-means Algorithm to Detect Learning Styles in Online Learning Environment,” J. Netw. Netw. Appl., vol. 4, p. 39, Jun. 2024, doi: 10.33969/J-NaNA.2024.040105.
[23]H.-H. Nguyen et al., “Applying machine learning techniques to detect student’s learning styles,” in Proceedings of the 14th International Conference on Education Technology and Computers, 2023, pp. 456–462. doi: 10.1145/3572549.3572622.
[24]T. Hussain, L. Yu, M. Asim, A. Ahmed, and M. A. Wani, “Enhancing E-Learning Adaptability with Automated Learning Style Identification and Sentiment Analysis: A Hybrid Deep Learning Approach for Smart Education,” Information, vol. 15, no. 5, p. 277, May 2024, doi: 10.3390/info15050277.
[25]Diwakar and D. Raj, “DistilBERT-based Text Classification for Automated Diagnosis of Mental Health Conditions,” in Microbial Data Intelligence and Computational Techniques for Sustainable Computing, Springer Nature Link, 2024, pp. 93–106. doi: 10.1007/978-981-99-9621-6_6.
[26]A. Vaswani et al., “Attention is All you Need,” in Advances in Neural Information Processing Systems, 2017, vol. 30.
[27]J. L. Ba, J. R. Kiros, and G. E. Hinton, “Layer Normalization,” Jul. 2016.
[28]F. P. Putri, “DistilBERT with Adam Optimizer Tuning for Text-based Emotion Detection,” IJNMT (International J. New Media Technol., vol. 10, no. 1, pp. 30–34, Jul. 2023, doi: 10.31937/ijnmt.v10i1.3170.
[29]D. Eng et al., “Automated coronary calcium scoring using deep learning with multicenter external validation,” npj Digit. Med., vol. 4, no. 1, p. 88, Jun. 2021, doi: 10.1038/s41746-021-00460-1.