A Novel Algorithm for Dynamic Student Profile Adaptation Based on Learning Styles

E-learning recommendation systems are used to enhance student performance and knowledge by providing differentiated instruction based on the students’ interests and learning styles (LSs), which are typically stored in student profiles. For such systems to be effective, the profiles need to be adaptable and reflect the students’ changing behaviour. In this paper, we introduce new algorithms that are designed to track student learning behaviour patterns, identify their LSs, and maintain dynamic student profiles within a recommendation system (RS). We also propose a new method to extract features that characterise student behaviour to identify student LSs with respect to the Felder-Silverman learning style model (FSLSM). To test the efficiency of the proposed algorithm, we present a series of experiments that use a dataset based on real students to demonstrate how our proposed algorithm can effectively model a dynamic student profile and adapt to changes in student learning behaviour. The results reveal that the students could effectively increase their learning efficiency and quality of the courses recommended when their LSs are identified using our method.