The implementation of Face Emotion Recognition (FER) technology in online classes opens up new opportunities to effectively monitor students' emotional responses and adjust the teaching approach. Through FER, instructors can monitor students' emotional responses to learning materials in real-time and enable quick adjustments based on individual needs. Additionally, this technology can also be used to detect the level of enthusiasm or lack thereof among students towards the learning process, allowing for the optimization of teaching strategies. This study focuses on the implementation of the YOLOv8 algorithm in detecting students' enthusiasm, comparing the performance of YOLOv8n, YOLOv8s, YOLOv8m, and YOLOv8l models. Test results show that YOLOv8n performs the best with an accuracy rate of 95.3% and a fast inference time of 62ms, enabling real-time object detection. Thus, the application of YOLOv8 in this context aims to detect students' enthusiasm in real-time and allows instructors to quickly adjust their approach to meet students' needs. Furthermore, this research contributes to improving the quality of online learning by providing insights into students' emotional engagement and serving as a tool to help instructors better understand and respond appropriately to students' emotions during the online learning process.