Makine Öğrenimi Yöntemleri ile Ergenlerde Akıllı Telefon Bağımlılığı Seviyesinin Tahmini: Karşılaştırmalı Bir Çalışma

Abstract

Ergenler arasında akıllı telefon bağımlılığı, zihinsel sağlık, akademik başarı ve günlük rutinler üzerindeki olası etkileri nedeniyle giderek artan bir endişe kaynağı haline gelmiştir. Bu çalışma, sosyal medya, oyun, eğitim, fiziksel aktivite, akademik ölçütler ve bilişsel göstergeler gibi değişkenleri içeren davranışsal bir veri seti kullanarak akıllı telefon bağımlılığı şiddetinin tahmin edilmesini amaçlamaktadır. Hedef değişken olan Addiction_Level (Bağımlılık Düzeyi), uygun bir şekilde kategorilere ayrılarak sınıflandırma problemi olarak modellenmiştir. Çalışma kapsamında, Lojistik Regresyon (LR), Karar Ağacı (DT), Rastgele Orman (RF), K-En Yakın Komşuluk (KNN), Destek Vektör Makineleri (SVM), Gradyan Artırımı (GB), XGBoost ve Çok Katmanlı Algılayıcı (MLP) dahil olmak üzere çeşitli denetimli makine öğrenmesi algoritmaları uygulanmış ve karşılaştırılmıştır. Bu algoritmalar arasında, LR ve MLP modelleri sırasıyla %98,67 ve %97,17 doğruluk oranlarıyla en yüksek performansı göstermiştir ve daha karmaşık topluluk yöntemlerinden daha iyi sonuçlar elde etmiştir. Elde edilen bulgular, davranışsal kalıplar ve akademik göstergelere dayanarak akıllı telefon bağımlılığı seviyelerinin, basit ancak sağlam modeller aracılığıyla etkili bir şekilde tahmin edilebileceğini göstermektedir. Bu çalışma, veri odaklı stratejiler yoluyla ergen nüfusundaki aşırı telefon kullanımını tespit etmeyi ve azaltmayı hedefleyen eğitimciler, psikologlar ve politika yapıcılar için değerli çıkarımlar sunmaktadır.

Keywords

• Akıllı telefon bağımlılığı
• Makine öğrenimi
• Sınıflandırma
• Sinir ağları

Teen Smartphone Addiction Level Prediction Using Machine Learning Models: A Comparative Study

Abstract

Smartphone addiction among teenagers has become a growing concern due to its effect on brain status, school grades, and daily routines. This study investigates the prediction of smartphone addiction severity using a behavioral dataset that includes features such as daily time spent on social media, gaming, education, physical activity, academic metrics, and cognitive indicators. The target variable, Addiction_Level, was modeled as a classification problem after appropriate binning. Eight different machine learning models were implemented and compared, including Logistic Regression (LR), Decision Tree (DT), Random Forest (RF), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Gradient Boosting (GB), XGBoost, and Multilayer Perceptron (MLP). Among these, LR and MLP methods obtained the highest accuracy, with 98.67% and 97.17%, respectively, outperforming more complex ensemble methods. The results suggest that simple yet robust models can effectively predict smartphone addiction levels based on behavioral patterns and academic indicators. This study offers valuable insights for educators, psychologists, and policy-makers aiming to detect and mitigate smartphone overuse in adolescent populations through data-driven strategies.

Keywords

• Smartphone addiction
• Machine learning
• Classification
• Neural network

References

1. Adeogba E., Barty P., O'Dwyer E., Guo M. Waste-to-resource transformation: gradient boosting modeling for organic fraction municipal solid waste projection. ACS Sustainable Chemistry and Engineering 2019; 7(12): 10460–10466.
2. Akçay B., Keçelioğlu Ş., Özen MS., Yılmaz Gökmen G., Yüce H. Effect of smartphone addiction level on manual and finger dexterity, hand grip strength, pinch grip strength, and thumb pressure pain threshold in university students. Addicta: The Turkish Journal on Addictions 2023; 10(2): 158–164.
3. Azami-Aghdash S., Amandi FA., Abdolahi HM., Naghibi D., Rezapour R. Smartphone addiction and its association with accident risk in Iranian adults. Scientific Reports 2025; 15(1): 22399.
4. Baoli L., Qin L., Shiwen Y. An adaptive k-nearest neighbor text categorization strategy. ACM Transactions on Asian Language Information Processing 2004; 3(4): 215–226.
5. Belic I., Winskel H., Allen K., Longstaff MG. Communication preferences and factors predicting smartphone addiction among four generations of Australians: gender and generational differences. Journal of Technology in Behavioral Science 2025; 10(2): 373-381.
6. Cavazos J., O'Boyle MFP. Method-specific dynamic compilation using logistic regression. ACM SIGPLAN Notices 2006; 41(10): 229–240.
7. Demir OB., Bilgin A., Yilmaz FT. Smartphone addiction among elderly individuals: its relationship with physical activity, activities of daily living, and balance levels. BMC Public Health 2025; 25(1): 965.
8. Erzincanli Y., Taş HG., Akbulut G., Büladi Çubukçu B., Ulaş S., Bayrakçeken E. Evaluation of university students' smartphone addiction levels according to certain variables. Journal of Inonu University Vocational School of Health Services 2023; 11(1): 1330–1343.

9. Figueroa-Quiñones J., Cjuno J., Morales-García WC., Salinas-Arias S. Psychometric properties of the smartphone addiction scale (SAS-SV) in adolescents in Peru. Humanities and Social Sciences Communications 2025; 12(1): 978.
10. https://www.kaggle.com/datasets/sumedh1507/teen-phone-addiction(Last Access:06.08.2025).
11. Hung MT., Hung LC., Zhou Q., Huang Z. Peer pressure, anxiety, and smartphone addiction among Chinese college students: a mediation analysis. BMC Psychology 2025; 13(1): 772.
12. Ibrahim M., Carman M. Comparing pointwise and listwise objective functions for random-forest-based learning-to-rank. ACM Transactions on Information Systems 2016; 34(4): 20.
13. Kingston D., Shekhar SK. Moderating effects of gender and place of residence on the relationship between loneliness and smartphone addiction. Mental Health and Social Inclusion 2025; 29(3): 224-234.
14. Kong L., Zhao M., Huang W., Zhang W., Liu J. The impact of academic anxiety on smartphone addiction among college students: the mediating role of self-regulatory fatigue and the moderating role of mindfulness. BMC Psychology 2025; 13(1): 354.
15. Kumban W., Cetthakrikul S., Santiworakul A. Smartphone addiction, screen time, and physical activity of different academic majors and study levels in university students. International Journal of Environmental Research and Public Health 2025; 22(2): 237.
16. Lam EP. Texture classification using wavelet decomposition. Proceedings of the IEEE International Conference on System of Systems Engineering 2008; 4724197.
17. Li Y., Bontcheva K. Adapting support vector machines for f-term-based classification of patents. ACM Transactions on Asian Language Information Processing 2008; 7(2): 7.
18. Li Q., Liu Z. Parental psychological control and adolescent smartphone addiction: roles of reactance and resilience. BMC Psychology 2025; 13(1): 139.
19. Liang H., Jiang K., Yan TA., Chen GH. XGBoost: an optimal machine learning model with just structural features to discover MOF adsorbents of Xe/Kr. ACS Omega 2021; 6(13): 9066–9076.
20. Meng Z., Min K., Ma R., Yang J., Zhang H., Li Q. The mediating effect of parental monitoring in the association between parent–child relationship harmony and smartphone addiction: findings from a nationwide youth survey in China. BMC Public Health 2025; 25(1): 1184.
21. Moriuchi E., Hollebeek LD., Lim WM. Consumers’ smartphone addiction: impact of engagement and app type on wellbeing. Journal of Business Research 2025; 194: 115379.
22. Okela AH. Egyptian university students’ smartphone addiction and their digital media literacy level. Journal of Media Literacy Education 2023; 15(1): 44–57.
23. Olson JA., Sandra DA., Veissière SPL., Langer EJ. Sex, age, and smartphone addiction across 41 countries. International Journal of Mental Health and Addiction 2025; 23(2): 937-945.
24. Raychev V., Bielik P., Vechev M. Probabilistic model for code with decision trees. ACM Sıgplan Notices 2016; 51(10): 731–747.
25. Solankure K., Sagare S., Bhoomika J. Prevalence of smartphone addiction and its impact on sleep quality among school-going students: a cross-sectional study. Journal of Ayurveda and Holistic Medicine 2025; 13(4): 3-11.
26. Sonbol HM., Abd El Mawgoud AS., Aly MA., AbdElhay ES. Parenting styles and suicidal probability of adolescents: the moderating role of social anxiety and smartphone addiction. Egyptian Journal of Neurology, Psychiatry and Neurosurgery 2025; 61(1): 68.
27. Tatu MK. Examining the correlation between smartphone addiction and social and emotional loneliness levels of nursing students. Journal of Psychiatric Nursing 2024; 15(2): 166–174.
28. Torkamani MH., Mokhtarinia HR., Vahedi M., Gabel CP. Relationships between cervical sagittal posture, muscle endurance, joint position sense, range of motion and level of smartphone addiction. BMC Musculoskeletal Disorders 2023; 24(1): 61.
29. Türkkan T., Bülbül K., Yilmaz HÖ., Meriç ÇS. The relationship between internet and smartphone addiction and body mass index: the mediating role of eating behaviors. Discover Public Health 2025; 22(1): 165.
30. Wang X., Gong H., Lin Y. The role of anxiety factors in predicting smartphone addiction mediated by metacognition among university students: a two-stage SEM-ANN approach. BMC Psychology 2025; 13(1): 148.
31. Waszkiewicz S., Krakowska-Madejska P., Puskarczyk E. Estimation of absolute permeability using artificial neural networks (multilayer perceptrons) based on well logs and laboratory data from Silurian and Ordovician deposits in SE Poland. Acta Geophysica 2019; 67(6): 1885–1894.
32. Ye T., Luo J., Chen Y., Huang Y., He M., Yang J., Wang T., Yao Q., Qu Y., Yang Z. The influence of meaning in life on smartphone addiction among nursing undergraduates: the mediating roles of professional identity and achievement motivation. BMC Nursing 2025; 24(1): 258.
33. Zhang Q., Ma X. The associations between destructive parenting practice and addiction behaviors in internet and smartphone: A three-level meta-analysis. Children and Youth Services Review 2024; 160: 107537.
34. Zhong G., Shu Y., Zhou Y., Li H., Zhou J., Yang L. The relationship between social support and smartphone addiction: the mediating role of negative emotions and self-contro., BMC Psychiatry 2025; 25(1): 167.
35. Zhou Y., Pei C., Yin H., Zhu R., Yan N., Wang L., Zhang X., Lan T., Li J., Zeng L., Huo L. Predictors of smartphone addiction in adolescents with depression: combing the machine learning and moderated mediation model approach. Behaviour Research and Therapy 2025; 189: 104749.