Using Facial Expression to Detect Emotion in E-learning System: A Deep Learning Method

摘要

E-learning system is becoming more and more popular among students nowadays. However, the emotion of students is usually neglected in e-learning system. This study is mainly concerned about using facial expression to detect emotion in e-learning system. A deep learning method called convo-lutional neural network (CNN) is used in our research. Firstly, CNN is introduced to detect emotion in e-learning system based on using facial expression in this paper. Secondly, the training process and testing process of CNN are described. To learn about the accuracy of CNN in emotion detection, three databases (CK+, JAFFE and NVIE) are chosen to train and test the model. 10-fold cross validation method is used to calculate the accuracy. Thirdly, we introduce how to apply the trained CNN to e-learning system, and the design of e-learning system with emotion detection module is given. At last, we propose the design of an experiment to evaluate the performance of this method in real e-learning system.