|
|
 |
| |
|
|
|
Advanced Predictive Modeling of Sport Commitment Using Machine Learning Among Fitness Center Users in Riyadh |
|
|
|
PP: 701-715 |
|
|
doi:10.18576/jsap/150323
|
|
|
|
Author(s) |
|
|
|
Yahya, M. Khatatbeh,
Bandar S. Alzahrain,
Mohammad A. Tashtoush,
Rawan Abdul Mahdi Neyef Al-Saliti,
|
|
|
|
Abstract |
|
|
| This paper studies the development and testing of advanced statistical and machine learning methods to predict
sport commitment using fitness center visitor data; examines how psychological and social factors influence sport commitment; investigates how sport commitment dimensions predict mental health outcomes; and compares the predictive accuracy of traditional statistical models with machine learning approaches. Using a cross-sectional quantitative design, the researchers analyzed data from 423 participants from Riyadh fitness centers. Validated instruments measured self-regulation, sport commitment, and mental health, and correlations, stepwise regression, structural equation modeling (SEM), and Random Forest analysis were used to assess model performance. Results showed that self-regulation significantly predicted sport commitment (β = 0.748, p < 0.001) but did not directly affect mental health. Sport commitment predicted mental health (β = 0.317, p < 0.001) and fully mediated the relationship between self-regulation and mental health. Mastery orientation and emotional support and social factors were among the strongest predictors, and the Random Forest model outperformed linear regression (R2 = 0.932). Overall, sport commitment appears to be the psychological mechanism linking self-regulation and
mental health. |
|
|
|
|
|
|
|
