How does students' perception of ChatGPT shape online learning engagement and performance?

Artiicial intelligence technologies, such as ChatGPT, Bert, LaMDA, and T5 have become deeply integrated into universities, influencing numerous functions within higher education and various aspects of students' lives. This article examined how students' perceptions of ChatGPT influence their engagement and performance in online learning, focusing on the mediating role of engagement. The perception of ChatGPT involves a student's understanding of, willingness to utilize, and concerns regarding the technology. These interconnected factors can influence students' online learning engagement with the software and, consequently, affect their academic performance. The study used self-reported data from 305 participants at a large university in Iran. The findings from Structural Equation Modeling (SEM) revealed that students' perception of ChatGPT accounts for 19.2 % of the variance in online learning engagement, while the combination of ChatGPT perception and online learning engagement explains 40.4 % of the variance in academic performance. Furthermore, students' perceptions of ChatGPT had direct effects on online learning engagement (β = 0.438) and academic performance (β = 0.268). Additionally, online engagement significantly mediated this relationship, with an indirect effect of β = 0.206. The observed direct and indirect effects highlighted the essential role of online learning engagement in fostering interaction and enhancing students' performance. Overall, our conceptual model provides researchers and university administrators with a comprehensive understanding of students' perceptions of ChatGPT, their engagement, and their academic performance in an online setting. This model also provides valuable insights for future research on designing student activities that leverage artificial intelligence technologies, including ChatGPT-based tools.