An integrated SEM-ANN approach to evaluating cybersecurity behaviors in the metaverse

The Metaverse is rapidly transforming virtual interactions, especially in education, but its growth also attracts cyber threats. Without understanding and addressing users’ cybersecurity behaviors, the Metaverse’s full potential is at risk, making investigating these behaviors a pressing necessity. Grounded on the theory of planned behavior (TPB), technology threat avoidance theory (TTAT), and protection motivation theory (PMT), this research develops an integrated theoretical model to evaluate users’ cybersecurity behaviors in the Metaverse. Data were gathered from 701 Metaverse users and were analyzed using a hybrid structural equation modeling-artificial neural network (SEM-ANN) approach. Of the 11 proposed hypotheses, the Partial Least Squares-Structural Equation Modeling results showed that nine were supported, explaining 63.1% of the variance in cybersecurity behavior. The ANN analysis revealed that avoidance motivation and attitude are the most significant factors influencing cybersecurity behavior. In addition to its theoretical contributions, the findings offer actionable insights for various stakeholders.