Creative Commons source reading · Machine learning for performance
Athletic identity and depressive symptom risk in college students: a machine learning approach to identify at-risk profiles and protective correlates
Chang D
Originally published in Front Psychol · 2026-06-05
From the article
Selected source text. JournalOS removes markup and shortens excerpts where indicated. The full article provides the complete context.
Abstract
AbstractThe relationship between athletic participation and depressive symptom risk among college students remains complex and contested, with prior research yielding inconsistent findings regarding whether sports involvement serves as a protective correlate or a correlate of psychological vulnerability. Using cross-sectional survey data from 795 undergraduate students at a large public university in the northeastern United States, this study employed machine learning methods to examine how athletic identity profiles, sports participation patterns, and related psychosocial correlates were associated with depressive symptoms. We specifically aimed to identify distinct athletic identity profiles, evaluate whether these profiles improved depression-risk prediction, and examine whether risky health behaviors and masculine norm variables…
Principal findings
We identified four athletic identity profiles with differential depression risk: Status-Oriented Athletes (45% depression), Non-Athletes (33%), Competitive Athletes (29%), and Recreational Athletes (24%). Machine learning models (Lundberg and Lee, 2017) achieved AUC = 0.78, with SR norms, risky drinking, and jock identity as top predictors; task orientation (Duda and Nicholls, 1992) was protective. Sex moderated relationships (jock identity stronger for males). Risky behaviors and masculine norms accounted for a statistically significant indirect association linking jock identity with depressive symptoms (31% of the total association in the specified model) (Preacher and Hayes, 2008). Findings support distinguishing status-oriented from mastery-oriented athletic identities (Brewer et al., 1993).
Theoretical implications
Athletic identity is multidimensional (status-seeking vs. mastery-oriented), not unitary; person-centered clustering better captures this complexity than traditional variable-centered approaches. Status-Oriented Athletes and Competitive Athletes may represent identity foreclosure risks (Murphy et al., 1996), while Recreational Athletes reflect healthy identity integration. Gender deeply moderates athletic identity: jock identity's stronger male effects reflect sports as masculinity-proving arenas (Connell, 2020). Weaker male–female differences in jock identity effects may, in turn, reflect women's access to alternative identity domains outside sport and a looser coupling between sport dominance and gender legitimacy. The findings are consistent with the possibility of dynamic reciprocal processes between identity, behavioral…
Editorial reading guide
- What data created and tested the model, and was evaluation independent?
- What is the cost of a false positive, false negative or out-of-distribution decision?
