Facial Micro-expression Modelling-Based Student Learning Rate Evaluation Using VGG–CNN Transfer Learning Model

Micro-facial expressions hold the potential to identify emotional states of students during their participation in online learning tasks. Through understanding the semi-nute facial cues, e-learning platforms can discern and decode a range of emotions experienced by students, including happiness, sadness, frustration, confusion, and more. This information can be used to personalize the learning experience for each student, provide early intervention and support, and improve engagement and motivation. This paper presents a VGG16 convolution neural network (CNN)-based transfer learning model for facial micro-expression recognition. The proposed model identifies the relation between micro-expressions and emotions in the student faces in online classes to assess the learning rate. Emotion modelling is used in the context of online education, and it entails making use of technology and data analysis to identify the emotional indicators that students are exhibiting and then responding appropriately. The pretrained VGG model allows for the creation of much deeper features than previous architectures while mitigating the vanishing gradient problem with the help of the transfer learning approach. The proposed model can learn more complex representations of the input data, which is important in recognizing subtle emotions, thereby accurately assessing the learning rate of the students. The proposed model obtained an accuracy of 97.3%.