Identifying Student Learning Styles using Support Vector Machine in The Felder-Silverman Learning Style Model

This research explores the intricate relationship between questionnaire structures and the accuracy of learning style predictions among students. Focusing on the balance between core and secondary questions, the study meticulously analyzes various ratios, emphasizing their impact on the learning style classification system. Through rigorous testing and integration of the Felder-Silverman Learning Style Model (FSLSM) with the Support Vector Machine (SVM) algorithm, the research uncovers crucial insights. Results showcase that a careful balance and distribution of questions significantly enhance the accuracy of predicting student learning styles, with accuracy rates reaching up to 89%. This study not only emphasizes the importance of personalized education but also demonstrates the practical applicability of advanced machine learning techniques. The findings provide a roadmap for the future of education, emphasizing a nuanced, question-specific approach for a more accurate, tailored, and responsive learning experience.