Understanding Factors Influencing Generative AI Use Intention: A Bayesian Network-Based Probabilistic Structural Equation Model Approach

This study investigates the factors influencing users' intention to use generative AI by employing a Bayesian network-based probabilistic structural equation model approach. Recognizing the limitations of traditional models like the technology acceptance model and the unified theory of acceptance and use of technology, this research incorporates novel constructs such as perceived anthropomorphism and animacy to capture the unique human-like qualities of generative AI. Data were collected from 803 participants with prior experience of using generative AI applications. The analysis reveals that social influence (standardized total effect = 0.550) is the most significant predictor of use intention, followed by effort expectancy (0.480) and perceived usefulness (0.454). Perceived anthropomorphism (0.149) and animacy (0.145) also influence use intention, but with a lower relative impact. By utilizing a probabilistic structural equation model, this study overcomes the linear limitations of traditional acceptance models, allowing for the exploration of nonlinear relationships and conditional dependencies. These findings provide actionable insights for improving generative AI design, user engagement, and adoption strategies.