Automatic Detection on Learning Styles using Support Vector Machine

Learning style plays a vital role in helping students retain learned concepts for a longer time and also improves the understanding of the concepts. This research project proposes an innovative approach to enhance the adaptability of Learning Management Systems (LMS) by automatically detecting and accommodating individual learning styles. The methodology combines a literature-based method and Support Vector Machine (SVM) algorithms to classify and profile learners based on their preferred learning styles. The literature-based method involves an extensive review and analysis of existing research on learning styles, encompassing various models and theories. The Support Vector Machine, a powerful supervised learning algorithm, is employed to develop a robust classification model. Leveraging the features extracted from the literature-based analysis, the SVM is trained to accurately categorize learners into distinct learning style profiles. The model’s effectiveness is validated using real-world data from a diverse set of learners within a Learning Management System. The results of this study provide valuable insights into the feasibility and effectiveness of combining literature-based methods with advanced machine learning techniques to enhance adaptive learning systems.