Abstract—The affective state is determinate to online learning quality. It is related to students’ attitude, learning motivation, and learning engagement. Learning affective states consists of engagement, frustration, confusion, and off-task state in this study. Different affective states are associated with different online learning behavior features. Affective states analysis consists of data collecting, data processing, affective states analyzing, evaluating, and intervening. Students’ affective states can be analyzed by the affective state detectors. 12,912 online learning operations from an online course are used to construct the affective state detectors and examine the effectiveness. The consistency of the analysis results with the self-reports supported that the model is reliable to analyze students’ affective state.
Index Terms—Research and application, online affective state; analysis model.
Yang Wang and Qingtang Liu are with the Central China Normal University, China (e-mail: wangyang0519@mails.ccnu.edu.cn, liuqtang@mail.ccnu.edu.cn).
David Stein is with the Ohio State University, USA (e-mail: stein.1@osu.edu).
Qihui Xia is with the Nanjing Normal University, China (e-mail: qihuixia1993@163.com).
Cite: Yang Wang, Qingtang Liu, David Stein, and Qihui Xia, "Measuring Students Affective States through Online Learning Logs — An Application of Learning Analytics," International Journal of Information and Education Technology vol. 9, no. 5, pp. 356-361, 2019.