Analysis and Prediction of Factors Affecting Student Grades in Online Collaborative Learning Using Genetic Programming-based Approach

Computer-supported collaborative learning (CSCL) has been widely adopted as an instructional method that utilizes computer technology to support and facilitate cooperation and collaboration in the learning process. In order to achieve high-quality collaborative learning and provide personalized instruction to students in a CSCL environment, it is necessary to analyze collaborative interaction characteristics and predict student performance. There are still some limitations to the existing studies due to the underutilization of data on the student collaboration process and the poor interpretability of the models used. Therefore, this study fully mines students’ collaborative session data, extracts relevant collaborative interaction features, and then constructs a student performance prediction model using the GP algorithm. Finally, we explored the accuracy of the GP model and validated it using another online collaborative course. The study showed that the GP prediction model was more accurate and stable than other machine learning methods, and the validation results in another course showed a high degree of consistency between student grades in the course and the model's predictions. In addition, the analysis results revealed that the number of statements, length of statements, and positive and negative emotions were the key factors affecting student grades in the CSCL environment. The findings help provide useful insights for further optimizing curriculum design and instructional interventions.