The relationship between physical activity and Internet addiction among Chinese adolescents: exploring latent profile analysis and multi-level mediating mechanisms

Abstract

In recent years, adolescent Internet addiction has emerged as a pressing concern, undermining young people's psychological well-being and social functioning. Although regular physical activity is known to bolster adolescents' mental health, its direct and indirect protective effects against Internet addiction-and the psychosocial processes involved-remain insufficiently understood, particularly in terms of how these effects differ across subgroups identified via latent profile analysis. Given this, the present study, employing structural equation modeling (SEM), delineated the factor structures and predictive relationships among physical activity, family cohesion, prosocial behavior, and Internet addiction. Moreover, to investigate how these pathways vary across different user groups, we conducted latent profile analysis (LPA) to identify distinct Internet-use typologies and tested their Mediation effects. The measurement model supported adequate construct validity and internal consistency across all latent variables, ensuring the reliability of subsequent structural analyses. SEM results demonstrated that physical activity exerted a significant negative direct effect on Internet addiction (β = -0.227, p < 0.001), and indirect effects via family cohesion (-0.065, 15.7% of total effect) and prosocial behavior (-0.083, 19.9% of total effect), as well as a chained pathway from family cohesion to prosocial behavior (-0.043, 10.1% of total effect). LPA supported a three-class solution-Functional Use (31.2%), At-Risk Use (49.5%), and Addicted Use (19.3%)-and multi-group SEM indicated that the magnitude of both indirect pathways varied across these typologies, with the strongest mediation observed in the At-Risk group. These findings suggest that physical activity is associated with reduced adolescent Internet addiction both directly and indirectly through socio-psychological mechanisms, and that intervention efforts should be tailored to specific user typologies to maximize preventive and remedial impact. These findings suggest that school-based physical activity interventions may help mitigate Internet addiction among Chinese adolescents.

Keywords: Internet addiction; family cohesion; latent profile analysis; physical activity; prosocial behavior.

Figure 1

Hypothesized model.

Figure 2

Correlation matrix among variables.

Figure 3

SEM test model.

Figure 4

Profiles of adolescent Internet addiction.

Figure 5

Latent profile analysis and path differences across Internet use categories. (a) Addicted use group β_IE = 0.046, P < 0.001 (95% CI, [−0.068, 0.032]). (b) At-Risk use group β_IE = 0.079, P < 0.001 (95% CI, [−0.064, 0.028]). (c) Functional use group β_IE = 0.079, P < 0.001 (95% CI, [−0.042, 0.006]).

Figure 6

(a) Measurement invariance test for chained mediation pathways across groups. (b) Structural path differences between Internet use types. (c) Bootstrap estimates of chained mediation effects across Internet use groups.