The impact of problematic social media use on adolescent subjective well-being: insights from machine learning - Summary - MDSpire

Examining the Effects of Challenging Social Media Engagement on Adolescent Well-Being: A Machine Learning Approach

  • By

  • Yuan Tian

  • July 20, 2026

Share

Objective:

To identify key predictors of adolescents’ subjective well-being (SWB) and examine the relationship between problematic social media use and SWB.

Approach:
  • Data Source: Data from the 2017/2018 Health Behaviour in School-aged Children (HBSC) survey, involving 187,090 adolescents aged 10 to 16.
  • Analytical Methods: Utilized XGBoost and multivariate logistic regression models to explore impacts of problematic social media use on SWB.
Key Findings:
  • All dimensions of problematic social media use, except for time reduction failure, were negatively associated with SWB.
  • Feeling escape and family conflict accounted for 49.26% of the total variance in SWB, while age and sex accounted for 25.5%.
  • Feeling escape, family conflict, increasing age, and female gender were significantly associated with lower SWB. Complex interaction patterns among these variables were also suggested.
Interpretation:

Future interventions should focus on emotional regulation skills, quality of family communication, and tailored support for older adolescents and girls.

Limitations:
  • The study is based on self-reported data, which may be subject to bias.
  • The cross-sectional design limits causal inferences.
Conclusion:

Identifying predictors of SWB is important for understanding the factors influencing adolescent well-being.

Original Source(s)

Related Content