A new emotion–based affective model to detect student’s engagement

• Main Authors: Khawlah Altuwairqi, Salma Kammoun Jarraya, Arwa Allinjawi, Mohamed Hammami
• Format: Article
• Language: English
• Published: Elsevier 2021-01-01
• Series: Journal of King Saud University: Computer and Information Sciences
• Subjects: Face expressions; Emotions; Engagement levels; Academic emotions; Affective model
• Online Access: http://www.sciencedirect.com/science/article/pii/S1319157818309224

Detecting student's engagement is an important key to improve an e-learning system. An e-learning system adapted to learner emotions is considered as an innovative system. Among the challenges that face researcher is how to measure student's engagement depending on their emotions. During the few years, several solutions were proposed to measure student’s engagement, but few solutions detect engagement level without consider if the student is learning or not. In this paper, we reviewed the current works of emotions and engagement level of student. According to that, we built our engagement level and linked them with the appropriate emotions. Then, we propose an affective model and a new process to detect final engagement level. The efficiency of the proposed Affective Model is shown experimentally by conducting a series of experiments. Firstly, we compute the Matching Score (MS) and Miss-matching Score (MisMS) for each engagement level. Secondly, we apply the new engagement level detection process on severe cases. Thirdly, we analyze all emotions in each level of engagement to detect strong emotions. We record matching score (MS) in range [71.2%, 100%]. Finally, we proposed some suggestions to improve the affective model.