Abstract

Understanding and predicting athletes' mental states is crucial for optimizing sports performance. This study introduces a hybrid BERT-XGBoost model to analyze psychological factors such as emotions, anxiety, and stress, and predict their impact on performance. By combining BERTs bidirectional contextual learning with XGBoosts classification efficiency, the model achieves high accuracy (94%) in identifying psychological patterns from both structured and unstructured data, including self-reports and observational data tagged with categories like emotional balance and stress. The model also incorporates real-time monitoring and feedback mechanisms to provide personalized interventions based on athletes psychological states. Designed to engage athletes intuitively, the system adapts its feedback dynamically to promote emotional well-being and performance enhancement. By analyzing emotional trajectories in real-time, it offers empathetic, proactive interactions. This approach optimizes performance outcomes and ensures continuous monitoring of mental health, improving human-computer interaction and providing an adaptive, user-centered model for psychological support in sports.