Exploring Learner Achievement Analysis using K-Means, SVM, and EM Clustering in a Unity-Based Virtual Reality Learning Environment

Abstract

This research article aims to analyze learner performance data from virtual reality environments developed with Unity using machine learning algorithms such as K-Means, Support Vector Machine (SVM), and EM clustering algorithms. The recent platform offers fun math and reading activities for sixth-grade students. With its deep integration capabilities, the learning platform collects extensive information about learner activities and interactions. We highlight in this empirical study the importance of the Unity virtual reality platform as a data collection tool and its influence on improving the learning experience. Our study used K-Means, SVM, and EM algorithms to identify groups of students with similar profiles (beginner, intermediate, and advanced) by analyzing trends within these groups. Thanks to these analyses, it is possible to understand the particular needs of learners better and this opens the way to more precise and tailor-made educational interventions. According to this analysis, the results obtained are beneficial for teachers to develop effective learning strategies adapted to the needs of students. Finally, this research highlights the possibility of transforming educational technology, specifically virtual reality like Unity, to facilitate decision-making and improve education.