Abstract—E-learning system based on formalized teaching but with the help of electronic resources is known as E-learning. Education has changed dramatically, with the distinctive rise of e-learning, whereby teaching is undertaken remotely and on digital platforms. However, when a student in a physical classroom he can ask questions from the instructor and reduce their stickiness. In addition, the instructor can easily identify if the student understands the lesson or not. But when it comes to the E-learning platforms identifying student satisfaction is challenging. In most E-learning platforms, there are discussion forums to ask questions. However, there is no proper way to identify each student’s problems, satisfaction with the lesson as a physical classroom. So this is the main issue here the authors identified in this research. Therefore, to avoid students' stickiness and improve the satisfaction in E-learning platforms here authors suggest a student satisfaction monitoring system for courses or the live sessions. For this here, the authors suggest a Data science approach-based solution. Here in the authors' solution, there are three main components combined to monitor student satisfaction. They are facial expression identifier, Speech analyzer, and the students' browser history analyzing component while in the lecturer. By these three components here, this application is able to analyze whether the student is satisfied with the lecture. The main goal of the author of this research is to increase student satisfaction by notifying each student’s satisfaction with the lecturer or the course owner
 

Index Terms—neural networks, E-Learning, data science, emotional recognition, satisfaction monitoring

Cite: K. T. Yasas Mahima and T. N. D. S. Ginige, "Students Behavioral and Emotional Detection Based Satisfaction Monitoring System for E-Learning," International Journal of Learning and Teaching, Vol. 8, No. 1, pp. 1-7, March 2022. doi: 10.18178/ijlt.8.1.1-7