Comparative Analysis of Exemplar-Based Approaches for Students’ Learning Style Diagnosis Purposes

Abstract

A lot of computational models recently are undergoing rapid development. However, there is a conceptual and analytical gap in understanding the driving forces behind them. This paper focuses on the integration between computer science and social science (namely, education) for strengthening the visibility, recognition, and understanding the problems of simulation and modelling in social (educational) decision processes. The objective of the paper covers topics and streams on social-behavioural modelling and computational intelligence applications in education. To obtain the benefits of real, factual data for modeling student learning styles, this paper investigates exemplar-based approaches and possibilities to combine them with case-based reasoning methods for automatically predicting student learning styles in virtual learning environments. A comparative analysis of approaches combining exemplar-based modelling and case-based reasoning leads to the choice of the Bayesian Case model for diagnosing a student’s learning style based on the data about the student’s behavioral activities performed in an e-learning environment.