Examining Metaverse Intention to Use Among Computer Science and Engineering Students Via UTAUT2, DOI Through PLS-SEM, ML & Network Analysis

Abstract

This study explores Engineering and Computer Science students’ inclination to adopt Metaverse systems by integrating the Unified Theory of Acceptance and Use of Technology 2 (UTAUT2) and the Diffusion of Innovations (DOI) models. To gain complementary insights authors employed a multi-analytical approach combining Partial Least Squares Structural Equation Modeling (PLS-SEM), Machine Learning (ML), and Network Analysis. The PLS-SEM analysis found “Facilitating Conditions” as significant predictor of Behavioral Intention (BI), while found “Price Value” have a minimal impact. Additionally, Compatibility, Complexity, and Observability unfold as key factors in Metaverse adoption. ML analysis found that Linear Discriminant Analysis outperforms other classifiers, showing high predictive accuracy (0. 882) for Behavioral Intention. Network analysis highlights the centrality of Behavioral Intention within the adoption network, confirming its crucial role and showing strong alignment with PLS-SEM findings. All these results together offer a comprehensive understanding of factors influencing Metaverse adoption, supporting aimed interventions and future research to enhance student engagement with Metaverse technologies.

Keywords: Metaverse, UTAUT2, DOI, PLS-SEM, Machine Learning, Network Analysis