Deciphering Patterns in Student Emotional Fluctuations: A Big Data Approach in Educational Psychology

With the rapid advancement of big data and information technology, the analysis of student emotional fluctuations has emerged as a new frontier in the field of educational psychology. This study aims to explore the patterns of student emotional fluctuations through big data analysis techniques and to use these patterns to predict students’ psychological tendencies, thereby providing educators with real-time, accurate teaching references. The importance of student emotions in the learning process and the potential of big data technology in perceiving and analyzing student emotions are elucidated in the background section. The current state of study discusses the limitations of traditional methods in analyzing student emotions, such as small sample sizes, short data collection time spans, and the lack of timeliness and accuracy in analysis. A student emotional fluctuation identification model based on big data is first established, capable of integrating multi-source data and effectively capturing subtle changes in student emotions. Furthermore, a psychological tendency mixed-frequency prediction model is constructed, utilizing the mixed data sampling (MIDAS) mixed-frequency model, aimed at achieving accurate predictions of trends in student emotional fluctuations. The development and validation of these two models demonstrate the application value of big data analysis in the field of educational psychology, supporting personalized learning and promoting the effectiveness of student emotional management and teaching interventions.