Engagement in LLM Chatbot-Supported Learning: The Pivotal Roles of GenAI Competency and Emotion

Synthesis: Huang and Zhang (2026) propose and test a theoretically grounded model of student engagement in LLM chatbot-supported learning, guided by appraisal theory. Unlike prior studies that focus on isolated antecedents, the model integrates learners' capacity appraisals (GenAI competency and academic self-efficacy), in-situ cognitive appraisals (perceived usefulness and ease of use of the chatbot), and affective appraisals (emotions experienced when using the chatbot). Based on 234 responses analyzed with structural equation modeling and mediation analyses, the study finds that GenAI competency had the strongest relationship with student engagement, emotion fully mediated the effect of perceived usefulness on engagement, and academic self-efficacy showed no significant direct association after accounting for other variables.

Key Findings

• GenAI competency had the strongest relationship with student engagement in chatbot-supported learning.
• Emotion fully mediated the effect of perceived usefulness on engagement.
• Perceived usefulness partially mediated the effect of perceived ease of use.
• Academic self-efficacy showed no significant direct association with engagement after accounting for other variables.
• The findings highlight the critical role of GenAI competency and positive emotions in chatbot-supported learning.

Implications for AI in Education

The study offers a differentiated model of Student Engagement in the context of chatbot-supported learning, highlighting the pivotal role of GenAI competency and positive emotions. For learning designers, the finding that GenAI competency most strongly drives engagement suggests that building students' AI skills is a prerequisite for meaningful engagement with AI tools, not an afterthought. The full mediation of perceived usefulness through emotion indicates that how students feel about the chatbot matters as much as how useful they perceive it to be. The null result for academic self-efficacy challenges assumptions about which learner characteristics drive engagement in AI contexts. The model connects to Self Efficacy, Motivation, and emotion research in AI education.

Connected Concepts

• Student Engagement
• Conversational AI
• Generative AI
• AI Literacy
• Self Efficacy
• Motivation
• Affective Computing
• Student Experience

Connected Articles

• [genai-motivation-engagement-2026] — GenAI motivation and engagement research
• [ai-student-engagement-online-learning-review-2025] — systematic review of AI applications for student engagement
• [genai-tutor-engagement-patterns] — multi-institution engagement patterns

Citation

Huang, X., & Zhang, S. (2026). Engagement in LLM chatbot-supported learning: The pivotal roles of GenAI competency and emotion. Computers and Education: Artificial Intelligence, 10, 100559.