Engagement in LLM chatbot-supported learning: The pivotal roles of GenAI competency and emotion

Student engagement, widely recognised as a key determinant of learning outcomes, warrants greater attention to its antecedent mechanisms for effective learning design. As LLM-based chatbots (hereafter chatbot) are increasingly used to support student learning, understanding what drives student engagement in such environments becomes especially important. Guided by appraisal theory, this study proposes a theoretically grounded model of students' engagement in chatbot-supported learning. Unlike prior studies that focus on isolated antecedents, the model integrates learners’ capacity appraisals, including technology-related (GenAI competency) and task-related (academic self-efficacy) dimensions, with in-situ cognitive appraisals (perceived usefulness and ease of use of the chatbot) and affective appraisals (emotions experienced when using the chatbot) to explain student engagement. Data were collected after students completed chatbot-supported learning tasks, resulting in 234 responses. Structural equation modelling and mediation analyses revealed that GenAI competency had the strongest relationship with student engagement. Emotion fully mediated the effect of perceived usefulness on engagement, while perceived usefulness partially mediated the effect of perceived ease of use. Notably, academic self-efficacy showed no significant direct association with engagement after accounting for the effects of other variables. These findings denote a differentiated model of student engagement in the context of chatbot-supported learning, highlighting the critical role of GenAI competency and positive emotions. They contribute to the literature on learning engagement and offer practical insights for designing AI-integrated learning environments that promote and sustain meaningful student engagement.