The association between coaching behaviors and athlete burnout among college athletes: an integrated SEM-ANN model based on self-determination theory.

Background: As competitive training pressure continues to rise in higher education, athlete burnout among university students has become more prominent and is often accompanied by lower motivation, reduced performance, and stronger intentions to withdraw from sport. Although prior studies have examined the association between coaching behaviors and athlete burnout, less attention has focused on how this association relates to basic psychological needs, and few studies have combined theory-based testing with predictive analysis. Guided by Self-Determination Theory, this study tested a parallel mediation model including autonomy-supportive and controlling coaching behaviors, autonomy, competence, relatedness, and athlete burnout. The study also examined gender differences. Methods: Questionnaire data were collected from 800 university student athletes in China using standardized scales. A two-stage analysis combining partial least squares structural equation modeling and artificial neural network analysis was then conducted. Results: Autonomy-supportive coaching behaviors were negatively associated with athlete burnout, whereas controlling coaching behaviors were positively associated with burnout. Autonomy, competence, and relatedness were all negatively associated with burnout and partially accounted for the associations between coaching behaviors and burnout. Among these needs, competence showed a relatively stronger indirect association. Multi-group analysis further showed that the indirect association between autonomy-supportive coaching behaviors and athlete burnout through autonomy was clearer in female athletes. Conclusion: These findings offer empirical support for adjusting coaching communication, fostering need-supportive training environments, and developing targeted psychological support strategies in university athletic settings.