Using Explainable Artificial Intelligence to Predict Internet Addiction in Turkish University Students

GEZGİN D. M., Efeoğlu E.

International Journal of Human-Computer Interaction, cilt.42, sa.4, ss.2012-2034, 2026 (SCI-Expanded, SSCI, Scopus) identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 42 Sayı: 4
  • Basım Tarihi: 2026
  • Doi Numarası: 10.1080/10447318.2025.2526587
  • Dergi Adı: International Journal of Human-Computer Interaction
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Social Sciences Citation Index (SSCI), Scopus, Academic Search Premier, ABI/INFORM, Applied Science & Technology Source, Business Source Elite, Business Source Premier, Compendex, Computer & Applied Sciences, INSPEC, Library and Information Science Abstracts, Linguistics & Language Behavior Abstracts, Psycinfo
  • Sayfa Sayıları: ss.2012-2034
  • Anahtar Kelimeler: artificial intelligence, Internet addiction, machine learning, XAI
  • Trakya Üniversitesi Adresli: Evet

Özet

The rising incidence of internet addiction (IA) among university students has raised concerns about its impact on academic performance, mental health, and social relationships. This study aims to model internet addiction in 1,180 university students using Explainable Artificial Intelligence (XAI) methods, including SHapley Additive Explanations (SHAP). Unlike traditional statistical approaches, such as linear regression, and opaque AI models like deep neural networks, XAI offers interpretable outputs that help reveal underlying factors contributing to IA. Student demographics, internet use patterns, and psychological variables were analyzed by machine learning algorithms, and SHAP was used to interpret the models. The findings reveal key predictors of IA, such as fear of missing out (FoMO), social anxiety, and social-emotional loneliness. By using XAI, the study shows how specific traits and behaviors elevate IA risk and offers actionable insights for educators and policymakers. It also supports early detection and intervention strategies in educational and psychological contexts.