Collaborative Analysis of Learners’ Emotional States Based on Cross-Modal Higher-Order Reasoning

Emotion is a significant factor influencing education and teaching, closely intertwined with learners’ cognitive processing. Conducting analysis of learners’ emotions based on cross-modal data is beneficial for achieving personalized guidance in intelligent educational environments. Currently, due to factors such as data scarcity and environmental noise, data imbalances have led to incomplete or missing emotional information. Therefore, this study proposes a collaborative analysis model based on attention mechanisms. The model extracts features from various types of data using different tools and employs multi-head attention mechanisms for parallel processing of feature vectors. Subsequently, through a cross-modal attention collaborative interaction module, effective interaction among visual, auditory, and textual information is facilitated, significantly enhancing comprehensive understanding and the analytical capabilities of cross-modal data. Finally, empirical evidence demonstrates that the model can effectively improve the accuracy and robustness of emotion recognition in cross-modal data.