Online Learning Engagement Recognition Using Bidirectional Long-Term Recurrent Convolutional Networks

• DOI: 10.3390/su15010198
• Publication Date: 2022-12-23T07:09:03Z
• Authors: Yujian Ma; Yantao Wei; Yafei Shi; Xiuhan Li; Yi Tian; Zhongjin Zhao
• Keywords: Student Engagement; Dropout (neural networks)

Background: Online learning is currently adopted by educational institutions worldwide to provide students with ongoing education during the COVID-19 pandemic. However, online has seen lose interest and become anxious, which affects performance leads dropout. Thus, measuring students’ engagement in imperative. It challenging recognize due lack of effective recognition methods publicly accessible datasets. Methods: This study gathered a large number videos at normal university. Engagement cues were used annotate dataset, was constructed three levels engagement: low engagement, high engagement. Then, we introduced bi-directional long-term recurrent convolutional network (BiLRCN) for video. Result: An dataset been constructed. We evaluated six using precision recall, where BiLRCN obtained best performance. Conclusions: Both category balance similarity data affect results; it more appropriate consider as process-based evaluation; can intervention strategies teachers from variety perspectives associated Dataset construction deep need be improved, management also deserves attention.