Detection of Student Impulse in the Classroom Using Facial Emotion Recognition

Emotions play a vital role in students' academic performance and overall well-being. However, detecting and understanding students' emotions remains a challenging task for educators. This study proposes a facial emotion recognition (FER) system to detect and analyse students' emotions in real-time, providing valuable insights for teachers to create a more supportive learning environment. Our FER model utilizes deep learning techniques to classify facial expressions into six basic emotions (happiness, sadness, anger, fear, surprise, and neutral). We collected a dataset of facial images from students during lectures and evaluated our model's performance. This research contributes to the development of affective computing in education, offering a non-invasive and objective emotion detection method. Our findings have implications for educators, policymakers, and researchers seeking to create emotionally intelligent learning environments.