Deep Analysis of Student Body Activities to Detect Engagement State in E-Learning Sessions

In this paper, we propose new 3D CNN prediction models for detecting student engagement levels in an e-learning environment. The first generated model classifies students' engagement to high positive engagement or low positive engagement. The second generated model classifies engagement to low negative engagement or disengagement. To predict the engagement level, the proposed prediction models learn the deep spatiotemporal features of the body activities of the students. In addition, we collected a new video dataset for this study. The new dataset was collected in realistic, uncontrolled settings from real students attending real online classes. Our findings are threefold: (1) Spatiotemporal features are more suitable for analyzing body activities from video data; (2) our proposed prediction models outperform state-of-the-art methods and have proven their effectiveness; and (3) our newly collected video dataset, which reflects realistic scenarios, contributed to delivering comparable results to current methods. The findings of this work will strengthen the knowledge base for the development of intelligent and interactive e-learning systems that can give feedback based on user engagement.

Automated summary

In this paper, new 3D CNN prediction models were proposed for detecting student engagement levels in an e-learning environment. The first model classifies engagement into high positive engagement or low positive engagement, while the second model classifies engagement into low negative engagement or disengagement. The models utilize deep spatiotemporal features of students' body activities to predict engagement levels. A new video dataset collected from real students attending online classes was used for this study. The findings suggest that spatiotemporal features are more suitable for analyzing body activities, the proposed models outperform state-of-the-art methods, and the newly collected dataset contributes to delivering comparable results to current methods. These findings are important for the development of intelligent and interactive e-learning systems that can provide feedback based on user engagement.