Using Artificial Intelligent Techniques to Classify Students Based on Their Preferred Learning Styles

Abstract

With the growing demand for e-learning, numerous studies have been conducted to enhance the quality of the education process. As a result of these studies, researchers have indicated that considering individual differences (learning styles) among students is a critical requirement for promoting student engagement and performance. Adaptive education systems use instruments to find out the preferences of students and hence can provide them with the materials and learning strategies that match their learning styles. The recent trend is to harness artificial intelligence classifiers to find out the learning styles of the learner automatically without disturbing the students.  This study aims to present an AI-based model that can effectively predict learning styles based on key input features. And the output learning styles include verbal, visual, passive, and active. This paper used a dataset from the authors' earlier work, and four machine learning classifiers were applied: Decision Tree, Random Forest, Support Vector Machine, and Neural Network. The experimental results indicate that machine learning algorithms can effectively classify and identify students’ learning styles.