1. TSSeer: a visual analytics approach for exploring the correlation between teachers' multimodal emotions and students' behaviors in massive open online courses.
- Author
-
Kui, Xiaoyan, Zhang, Mingkun, liu, Qiang, Wang, Zixiao, Huang, Guiping, Zheng, Zhihao, Xia, Jiazhi, and Zhang, Chao
- Abstract
Massive open online courses (MOOCs) have become a popular platform owing to their open nature. However, the shortage of emotional interaction in MOOCs can cause a high attrition rate among learners. Appropriate emotional expression can enhance knowledge delivery and students' learning performance. To tackle this issue, exploring the correlation between teachers' emotions and students' learning behaviors is of great value for instructors to understand how their emotions can impact students' learning performance and improve their teaching skills. However, manually watching and studying MOOCs videos are often tedious and time-consuming. There is a lack of efficient methods to help users conduct correlation exploration, which is challenging due to the large-scale, multi-dimensional, and time-series nature of students' learning behaviors and their complex correlation to teachers' multimodal emotions. In this paper, we propose an interactive visual system called TSSeer to facilitate correlation analysis in MOOCs videos. Specifically, the level view and correlation view allow users to obtain a quick overview of the correlation at different video levels. The detail view shows detailed temporal changes and enables a deeper understanding of the correlation with time-series visualization. Through comprehensive evaluations, including two usage scenarios and five expert interviews, the effectiveness and usefulness of TSSeer are demonstrated. [ABSTRACT FROM AUTHOR]
- Published
- 2024
- Full Text
- View/download PDF