Using Machine Learning and SEM to Analyze Attitudes towards adopting Metaverse in Higher Education

Abstract

The Metaverse has become a highly discussed topic in recent times, as it has the potential to transform many aspects of our lives. From banking and investing to real estate, manufacturing, and education, the Metaverse could change how we operate in many industries. This research paper aims to investigate the level of user acceptance and attitude toward the integration of the Metaverse technology into higher education in Bahrain and Jordan by employing the Technology Acceptance Model along with three external variables, self-efficacy, subjective norms, and perceived behavior control. A two-stage analysis was performed, consisting of structural equation modeling and machine learning classification algorithms. SEM results suggest that self-efficacy and social norms positively influenced perceived usefulness and ease of use, it is also found that perceived ease of use and perceived usefulness significantly affected users’ attitudes toward using this technology. Machine learning findings supported SEM results and indicated that J48, LogitBoost, and PART classifiers have achieved the highest accuracy.