Skip to main content

ORIGINAL RESEARCH article

Front. Public Health
Sec. Public Health Policy
Volume 13 - 2025 | doi: 10.3389/fpubh.2025.1511129

What factors influence the willingness and intensity of regular mobile physical activity？-A machine learning analysis based on a sample of 290 cities in China

Provisionally accepted
Hao Shen Hao Shen 1Bo Shu Bo Shu 2*Jian Zhang Jian Zhang 2*Yaoqian Liu Yaoqian Liu 3*Ali Li Ali Li 4*
  • 1 School of Architecture, Southwest Jiaotong University, Chengdu, China
  • 2 School of Design, Southwest Jiaotong University, Chengdu, China
  • 3 SWJTU-LEEDS Joint School, Southwest Jiaotong University, Chengdu, China
  • 4 Information and Network Management Center, Xihua University, Chengdu, Sichuan Province, China

The final, formatted version of the article will be published soon.

    This study based on VGI and multi-source data, employs machine learning methods to innovatively construct an interpretable macro-scale analytical framework. Using the 290 prefecture-level cities in China as samples, it systematically investigates the impact and underlying mechanisms of socioeconomic, geographical environment, and built environment factors on both the overall level and different types of mobile physical activities. Through empirical analysis, the study clearly reveals the specific effects of these factors at both the overall and activity-specific levels, as well as their interactions, providing comprehensive theoretical support for understanding and optimizing physical activity among urban residents. The results indicate: (1) There's a significant difference in the influencing factors of activity willingness and activity intensity; socio-economic factors are the primary influence on activity willingness, while activity intensity is more deeply affected by geographical environmental factors and built environmental factors; (2) The differences in activity types and the interactive relationship with influencing factors are significant. Regardless of the willingness or intensity of exercise, Low-threshold activities tend to amplify the promotional or inhibitory effects of influencing factors; (3) Consistent with micro-scale studies, some influencing factors exhibit typical nonlinear effects. Finally, based on the above conclusions and drawing from previous research, this study proposes guideline-based macro-level intervention measures from the perspective of effective public resource allocation. These measures aim to assist policymakers in developing more scientific and effective intervention strategies to enhance physical activity levels.

    Keywords: physical activity, Willingness and Intensity, Socioeconomic Factors, Geographical Environmental Factors, built environmental factors, machine learning, Mechanisms of influence

    Received: 14 Oct 2024; Accepted: 07 Jan 2025.

    Copyright: © 2025 Shen, Shu, Zhang, Liu and Li. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Bo Shu, School of Design, Southwest Jiaotong University, Chengdu, China
    Jian Zhang, School of Design, Southwest Jiaotong University, Chengdu, China
    Yaoqian Liu, SWJTU-LEEDS Joint School, Southwest Jiaotong University, Chengdu, China
    Ali Li, Information and Network Management Center, Xihua University, Chengdu, 610039, Sichuan Province, China

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.