Affiliation:
1. Jiangxi University of Finance and Economics
Abstract
Abstract
When real-time detection indicates a low level of student engagement in online classrooms, selecting an appropriate time for feedback can enhance learner engagement. To address this issue, this study proposes an Interval-valued q-rung orthopair fuzzy warning feedback model based on the evaluation of online learning engagement. The designed warning feedback model utilizes a sliding window to capture the linguistic evaluation results of facial expressions, eye gaze, and limb states of online learners. By employing the developed IVq-ROFWDBM operator, as well as feature weight derivation and sample point weight derivation methods, the fuzzy comprehensive evaluation of sample points within the sliding window is conducted. When the evaluation result indicates low engagement, timely feedback is provided to the learners. The implementation of case studies demonstrates that the proposed warning feedback model can provide timely and effective feedback, avoiding the contradiction between excessive and untimely feedback. Comparative analysis results indicate that the proposed operator can obtain more accurate feedback outcomes.
Publisher
Research Square Platform LLC
Reference43 articles.
1. How many ways can we define online learning? a systematic literature review of definitions of online learning (1988–2018);Singh V;American Journal of Distance Education,2019
2. Deeplms: a deep learning predictive model for supporting online learning in the covid-19 era;Dias SB;Scientific Reports,2020
3. OU Analyse: analysing at-risk students at The Open University;Kuzilek J;Learning Analytics Review,2015
4. Niu X, Han H, Zeng J, Sun X, Shan S, Huang Y, Chen X (2018, October). Automatic engagement prediction with gap feature. In Proceedings of the 20th ACM International Conference on Multimodal Interaction 599–603
5. Three-dimensional DenseNet self-attention neural network for automatic detection of student’s engagement;Mehta NK;Applied Intelligence,2022