AI performance assessment in blended learning: mechanisms and effects on students' continuous learning motivation

Introduction: Blended learning combines the strengths of online and offline teaching and has become a popular approach in higher education. Despite its advantages, maintaining and enhancing students' continuous learning motivation in this mode remains a significant challenge.

Methods: This study utilizes questionnaire surveys and structural equation modeling to examine the role of AI performance assessment in influencing students' continuous learning motivation in a blended learning environment.

Results: The results indicate that AI performance assessment positively influences students' continuous learning motivation indirectly through expectation confirmation, perceived usefulness, and learning satisfaction. However, AI performance assessment alone does not have a direct impact on continuous learning motivation.

Discussion: To address these findings, this study suggests measures to improve the effectiveness of AI performance assessment systems in blended learning. These include providing diverse evaluation metrics, recommending personalized learning paths, offering timely and detailed feedback, fostering teacher-student interactions, improving system quality and usability, and visualizing learning behaviors for better tracking.