Predictive Modeling Of Student Behavior In Virtual Reality: A Machine Learning Approach

• In Event: Computational Thinking and Cognitive Skill Development

Abstract

In the ever-evolving landscape of education, Virtual Reality (VR) environments offer a promising avenue for enhancing student engagement and learning experiences. This study demonstrates how machine learning (ML) can predict student behavior in educational Virtual Reality (VR) environments. Using a dataset of student interactions and movements from a VR orientation, we developed predictive models. Our regression model accurately forecasted continuous engagement scores with high accuracy (hold-out R2≈0.98). Additionally, a classification model correctly categorized engagement levels with 84.9% accuracy (κ=0.77). These results confirm the feasibility of applying real-time predictive analytics in VR to understand student behavior, revealing hidden patterns and enhancing immersive learning experiences.

Authors

• Prabeen Giri, Truman State University

• Gayathri Sadanala, Truman State University

• Xinhao Xu, University of Missouri

• Hao He, Emporia State University

• Jhon Bueno-Vesga, Pennsylvania State University