Prediction of Electronics Engineering Student's Learning Style using Machine Learning

Abstract

The learning style of students is oftentimes not considered in teaching strategies in an engineering program and as a result, educators used teaching strategies not suited to the majority's preference, students become inattentive and unresponsive in an e-learning class. The study was conducted to identify and predict the learning style of third-year electronics engineering students using the Visual, Auditory, Reading/Writing, and Kinesthetic Model (VARK). The significance of the study is the use of machine learning to automatically predict the student's style of learning. The prediction of learning style was divided into two: single-modal learning style and multi-modal learning style. Results show that 87% are a single-modal type of learners and only 13% are a multi-modal type. The Decision Tree is the optimized prediction model for the study. This study would provide faculty an efficient way of determining the learning style of their students and in effect, faculty will be able to adjust teaching strategies that match the learning style of the students.