Emotions at the heart of learning: exploring the role of teacher emotions in student engagement using facial emotion recognition

This study aims to use facial emotion recognition (FER) to investigate the influence of teachers' emotions on student engagement to gain a comprehensive understanding of the dynamics between teachers' emotional expressions and student engagement in the classroom. A pre-trained deep learning MTCNN model was used for face detection and a modified VGG16 CNN model for FER. The emotions of teachers are recorded, analysed and compared with the emotions, state of the students and their engagement levels. Findings show the contagious nature of emotions as students tend to mirror and respond to the emotional states conveyed by their teachers. The results also highlight that students typically experience heightened engagement and attention at the beginning of a lecture and drop midway through the lecture. This research underscores the importance of differentiated strategies and modes of instruction while also emphasising the importance of equipping educators with emotional intelligence and effective emotion management skills.