AI Performance Assessment in Blended Learning: Mechanisms and Effects on Students’ Continuous Learning Motivation

Provisionally accepted

Blended learning, which integrates the advantages of both online and offline teaching, has been widely adopted in higher education. However, effectively enhancing students’ continuous learning motivation within this teaching mode remains a challenge.Based on questionnaire surveys and structural equation modeling, we investigate the impact of AI performance assessment on students’ continuous learning motivation in blended learning. The results show that AI performance assessment enhances students’ continuous learning motivation through expectation confirmation, perceived usefulness, and learning satisfaction. However, AI performance assessment alone does not directly lead to continuous learning motivation in a blended learning environment. Based on these findings, this paper proposes measures to optimize the effectiveness of AI performance assessment systems in blended learning environments, including, but not limited to providing diverse evaluation metrics, personalized learning path recommendations, timely and detailed performance feedback, enhancing teacher-student interaction, improving system quality and usability, and tracking and visualizing learning behaviors.