Automatic Measurement and Visual Analysis of Students’ Cognitive Engagement in Course Learning

The measurement and analysis of cognitive engagement (CE) is essential for improving learning performance. Artificial intelligence (AI) is an important engine for developing new quality productive forces in education and the application of AI could enhance the objectivity and comprehensiveness of CE measurement. However, current research remains limited in applying AI to measuring CE within the classroom course learning context. To address this, the research developed a novel approach to automatically measure and visually analyze CE in course learning by using AI. Firstly, a six-level CE structure was explicitly defined in accordance with Bloom's Revised Taxonomy. Then, students' learning activities and learning scores were tracked and recorded by the learning management system (LMS). Based on these data, the CE level was recognized and measured automatically by employing text analysis technology. The contribution of each CE level on learning performance was calculated using a random forest model and visualized through partial dependence plots. An experiment was carried out, and the results demonstrated the effectiveness of this approach.