Generative AI-supported illustration learning in higher education: E-learning system quality and student participation intention

This study examines how e-learning system quality influences university students’ participation intention in generative artificial intelligence (GAI)-supported illustration learning. Drawing on the stimulus-organism-response (SOR) framework, it conceptualises such learning as a technology-enhanced creative context where GAI tools mediate students’ creative exploration and learning activities. Survey data from 791 students were analysed using Partial Least Squares Structural Equation Modeling (PLS-SEM) and Necessary Condition Analysis (NCA), together with multigroup comparisons between art and non-art majors. The findings show that interface design, reliability, and responsiveness jointly shape perceived e-learning system quality and act as its necessary conditions, while students’ attitudes toward GAI-supported illustration learning are a critical prerequisite for participation intention. Although system quality and perceived value positively contribute to participation intention, they are not necessary conditions. Multigroup analysis reveals a significant disciplinary difference: responsiveness has a stronger effect on system quality among non-art majors. This study offers empirical insight into the link between system quality and participation intention, with implications for integrating generative AI into creative learning environments in higher education.