Explainable machine learning prediction of internet addiction among Chinese primary and middle school children and adolescents: a longitudinal study based on positive youth development data (2019–2022)
Depression, anxiety, and family dynamics are significant factors influencing IA in children. The Extra Random Forest model proves most effective in predicting IA, emphasising the importance of addressing these factors to promote healthy digital habits in children. This study presents an effective SHAP-based explainable ML framework for IA prediction in children and adolescents.
Authors
- Lihua Jiang
- Zongyuan Ge
- Jingsong Luo (ORCID: https://orcid.org/0000-0001-5427-7011)
- Jiahe Liu (ORCID: https://orcid.org/0000-0002-1978-3338)
- Yuxin Chen (ORCID: https://orcid.org/0000-0001-5955-687X)
- Lang Chen (ORCID: https://orcid.org/0000-0003-3563-601X)
- Linlin Fan
- Huiyu He (ORCID: https://orcid.org/0009-0000-8419-5025)
- Shu‐Fen Liao (ORCID: https://orcid.org/0000-0003-0943-0667)
- Kexin Yu
- Chan Yong
Institutions
- The University of Melbourne (AU)
- Chinese University of Hong Kong (HK)
- Peking University (CN)
- Sichuan University (CN)
- West China Medical Center of Sichuan University (CN)
- Hong Kong Jockey Club (HK)
- Monash University (AU)
Publication Details
- Journal
- Frontiers in Public Health
- Published
- 2025-07-16
- DOI
- https://doi.org/10.3389/fpubh.2025.1590689
- Citations
- 5
- Primary Topic
- Impact of Technology on Adolescents
- Type
- article
- Field-Weighted Citation Impact
- 21.01
Funders
- National Natural Science Foundation of China
- Hong Kong Polytechnic University