PURPOSE: This study examines how social support influences adolescents' autonomous physical learning behavior, exploring the mediating roles of self-efficacy and exercise motivation, and the moderating effects of gender and behavioral typologies. The goal is to provide insights into how social support can enhance adolescents' engagement in physical activities and inform intervention strategies.
METHODS: A total of 2,359 junior high school students (1,208 males and 1,151 females; mean age = 13.21 ± 0.96 years) from three public schools in Shandong Province were surveyed between October and December 2024. Participants completed the Chinese versions of the Perceived Social Support Scale (PSSS), General Self-Efficacy Scale (GSES), Motivation for Physical Activity Measure-Revised (MPAM-R), and Autonomous Physical Learning Behavior Scale (APLBS). Data were analyzed using SPSS 25.0 for descriptive statistics, Pearson correlations, t-tests, one-way ANOVAs, and hierarchical regression; Mplus 8.3 for Latent Profile Analysis (LPA); and AMOS 27.0 for Structural Equation Modeling (SEM) with bootstrapping (10,000 resamples).
RESULTS: indicated significant positive correlations among social support, self-efficacy, exercise motivation, and autonomous physical learning (all p < .01). Hierarchical regression showed that social support accounted for 27.3% of the variance in autonomous learning behavior (β = 0.524, p < .001), self-efficacy explained an additional 5.8% (β = 0.279, p < .001), and exercise motivation explained a further 4.0% (β = 0.219, p < .001), resulting in a total R2 = 0.373. LPA identified four behavioral profiles-Highly Engaged (26.3%), Positively Regulated (35.7%), Selectively Participative (22.2%), and Passively Participative (15.8%)-with the four-class model demonstrating optimal fit (entropy = 0.921; AIC = 37,951.9; BIC = 38,081.6; BLRT p < .001; LMR p = .0235). SEM results (CMIN/DF = 3.546; GFI = 0.970; CFI = 0.985; TLI = 0.976; NFI = 0.979; RMSEA = 0.060) showed that social support had a direct effect on autonomous learning behavior (β = 0.325, p < .001) and a total indirect effect of 0.191 (total effect = 0.516, p < .001). Specifically, self-efficacy mediated 22.19% (β = 0.114, 95% CI [0.093, 0.137]), exercise motivation mediated 11.18% (β = 0.057, 95% CI [0.043, 0.074]), and the chain pathway (social support → self-efficacy → exercise motivation → learning) accounted for 3.49% (β = 0.018, 95% CI [0.012, 0.024]) of the total effect. Multi-group SEM indicated that the SS → SE → EM mediation path was stronger for females (β = 0.127, 95% CI [0.104, 0.152]) than for males (β = 0.088, 95% CI [0.070, 0.109]). Across latent profiles, the full sequential mediation (SS → SE → EM → APLB) was significant for Positively Regulated (β = 0.074, 95% CI [0.051, 0.101]) and Selectively Participative (β = 0.066, 95% CI [0.042, 0.089]) groups, marginally significant for Passively Participative (β = 0.038, 95% CI [0.015, 0.062]), and non-significant for Highly Engaged (β = 0.013, 95% CI [-0.004, 0.031]).
CONCLUSION: These findings demonstrate that social support enhances adolescents' autonomous physical learning both directly and indirectly through self-efficacy and exercise motivation. Psychological resilience processes accounted for approximately 37.1% of behavioral variance, and gender differences and latent profiles moderated these pathways. Interventions should therefore focus on strengthening perceived support to boost self-efficacy and motivation-especially among female and moderately engaged students-while tailoring strategies to each behavioral profile to foster sustained autonomous learning and lifelong physical activity engagement.Keywords: Machine Learning, Neural Networks, artificial intelligence.