EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

The dual effects of individual and contextual factors on adolescent problematic internet use: Machine learning approaches and SHAP explanations

Ke Huang iD, Yuyao Yang iD, Linxin Wang iD, Jianbin Li iD, Diyang Qu iD, Runsen Chen iD, Xinli Chi iD

Journal of Behavioral Addictions · 02.04.2026 · 15 (1) · 274-288

DOI: 10.1556/2006.2025.00160 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Behavioral Addictions, erschienen am 02.04.2026. Verfasst von Ke Huang und 6 weiteren Autor:innen. Beteiligte Einrichtung: 1School of Psychology, Shenzhen University, Shenzhen, China. Hauptthemen laut MEDLINE: Adolescent Behavior, Machine Learning, Internet Addiction Disorder. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 156 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Humanities and Social Sciences of Ministry of Education Planning Foundation, Revtalization Project of Humanities & Social Sciences, Shenzhen University, Youth Research Project of Shenzhen University 2035 Outstanding Research Plan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Purpose

This study applied the Interaction of Person-Affect-Cognition-Execution (I-PACE) model and the Relational Development System Theory (RDS) to identify key individual and contextual correlates of adolescents' problematic Internet use (PIU) with machine learning approaches.

Methods

Data from 68,425 adolescents were analyzed using five ensemble models (AdaBoost, Random Forest, LightGBM, Bagging, CatBoost) within a nested cross-validation framework. Key factors were identified through SHapley Additive exPlanations (SHAP), while bivariate partial dependence analyses were used to identify interactions.

Results

The prevalence of PIU risk was 23.2%. Five algorithms achieved comparable performance. CatBoost achieved the best performance and was selected as the final predictive model. SHAP values showed that the top 17 features explained nearly 80% of the model. At the individual level, intolerance of uncertainty was the strongest risk factor, whereas mindfulness was the main protective factor. Additionally, weekend video game time was a major behavioral risk contributor. At the contextual level, home-leaving intentions and bullying perpetration were identified as key family- and peer-related risk factors, respectively. Bivariate partial dependence analyses found both within–individual (e.g., mindfulness * intolerance of uncertainty) and individual–contextual (e.g., mindfulness * home-leaving intentions) interaction effects.

Conclusions

This study applied five machine learning algorithms to identify key individual and contextual factors associated with adolescent PIU risk and their interactions. The results suggest that risk factors accumulate across systems and impair adolescents' adaptive capacity, whereas mindfulness exerts cross-system effects that buffer these risks, offering implications for targeted interventions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Adolescent BehaviorMachine LearningInternet Addiction DisorderHumansAdolescentFemaleMalePredictive Learning ModelsRisk FactorsBoosting Machine Learning AlgorithmsPrediction AlgorithmsRandom Forest

Stichwörter der Autor:innen

I-PACE modelRDS theoryadolescent problematic Internet usemachine learningprediction model

Autor:innen und Institutionen

  • 1School of Psychology, Shenzhen University, Shenzhen, China.
  • 2Key Laboratory of Brain Cognition and Emotional Health of Guangdong Higher Education Institutes, Shenzhen University, Shenzhen, China.
  • 3Shenzhen Key Laboratory of Affective and Social Cognitive Science, Shenzhen University, Shenzhen, China.
  • 4Faculty of Psychology, Beijing Normal University, Beijing, China.
  • 5Department of Early Childhood Education, The Education University of Hong Kong, Hong Kong, China.
  • 6Vanke School of Public Health, Tsinghua University, Beijing, China.

ORCID-Profile: Ke Huang, Yuyao Yang, Linxin Wang, Jianbin Li, Diyang Qu, Runsen Chen, Xinli Chi

Förderung

  • Humanities and Social Sciences of Ministry of Education Planning Foundation
  • Revtalization Project of Humanities & Social Sciences, Shenzhen University
  • Youth Research Project of Shenzhen University 2035 Outstanding Research Plan

Zitieren

APA

Huang, K., Yang, Y., Wang, L., Li, J., Qu, D., Chen, R., & Chi, X. (2026). The dual effects of individual and contextual factors on adolescent problematic internet use: Machine learning approaches and SHAP explanations. Journal of Behavioral Addictions, 15(1), 274-288. https://doi.org/10.1556/2006.2025.00160

Vancouver

Huang K, Yang Y, Wang L, Li J, Qu D, Chen R, et al. The dual effects of individual and contextual factors on adolescent problematic internet use: Machine learning approaches and SHAP explanations. Journal of Behavioral Addictions. 2026;15(1):274-288. doi:10.1556/2006.2025.00160

BibTeX
@article{Huang2026,
  author = {Huang, Ke and Yang, Yuyao and Wang, Linxin and Li, Jianbin and Qu, Diyang and Chen, Runsen and Chi, Xinli},
  title = {The dual effects of individual and contextual factors on adolescent problematic internet use: Machine learning approaches and SHAP explanations},
  journal = {Journal of Behavioral Addictions},
  year = {2026},
  volume = {15},
  number = {1},
  pages = {274--288},
  doi = {10.1556/2006.2025.00160}
}
Kostenlos starten →