Utilizing AI to Extract Emotional Information from Learners to Enhance Online Learning Experience

In the digital age, computer programming courses have become a core component of higher education, essential for cultivating logical thinking and problem-solving skills. However, due to the complexity of programming languages and the characteristics of the online learning environment, students often struggle with emotional challenges that negatively impact their learning outcomes. Traditional teaching methods often fail to accurately and timely understand students' emotional states, which limits the effectiveness of interventions. This study explores the use of Artificial Intelligence (AI) technology to extract Emotional Information (EI) from learner data and proposes an emotional analysis model to enhance the online learning experience. The model analyzes students' text data on online learning platforms, such as discussion posts and assignment feedback, to monitor their emotional states during the learning process. Based on the monitoring results, personalized intervention strategies are provided to offer targeted support and guidance. Compared to traditional methods, our AI-based model offers more accurate and real-time emotional monitoring, enabling more effective and personalized interventions. The experiment was conducted in a university computer programming course with 80 students selected as research subjects. Results show that students in the experimental group, who used the model, performed better in learning satisfaction (increased from 3.5 to 4.2 out of 5), emotional positivity (positive emotions increased from 30% to 45%), and programming ability improvement (assignment scores increased from 70 to 80) than the control group. This study provides a new perspective and method for teaching practice in university computer programming courses, demonstrating the potential of AI to enhance educational outcomes by addressing students' emotional needs.