Classification of the Impact of Lifestyle and Technology Use on Mental Health Using Deep Learning Methods

Öz

This study aims to classify individuals’ mental health status by analyzing the impact of lifestyle and technology usage habits through deep learning methods. The dataset includes digital behavior and lifestyle indicators from 1,000 participants across Germany, Australia, India, the USA, Canada, and the UK. Key variables include screen time, social media usage, sleep duration and quality, stress level, physical activity, and productivity. After preprocessing—filling missing values with median, encoding categorical variables, and standardizing features—the data were split into 80% training and 20% testing sets. Four classification models were applied: Multi-Layer Perceptron (MLP), Long Short-Term Memory (LSTM), Autoencoder+MLP, and Decision Tree+MLP. Models were evaluated using accuracy, precision, recall, F1-score, and ROC curves. Findings revealed that the Decision Tree+MLP hybrid model achieved the highest performance with 90% accuracy, 92% precision, 85% recall, and 88% F1-score. While other models struggled to distinguish the “Chronic” mental health class, this hybrid model provided balanced and effective classification across all categories. In conclusion, digital behavior patterns and lifestyle indicators are significant predictors of mental health status, and AI-based models can uncover these relationships with high accuracy.

Anahtar Kelimeler

• Lifestyle
• technology usage
• mental health
• deep learning

Yaşam Tarzı ve Teknoloji Kullanımının Ruh Sağlığı Üzerindeki Etkilerinin Derin Öğrenme Yöntemleri ile Sınıflandırılması

Öz

Bu araştırmanın amacı, bireylerin yaşam tarzı ve teknoloji kullanım alışkanlıklarının ruh sağlığı üzerindeki etkilerini derin öğrenme yöntemleriyle analiz ederek zihinsel sağlık durumlarını sınıflandırmaktır. Çalışmada Almanya, Avustralya, Hindistan, ABD, Kanada ve İngiltere’den 1.000 katılımcıya ait dijital davranış ve yaşam tarzı verileri kullanılmıştır. Veri setinde ekran süresi, sosyal medya kullanımı, uyku süresi ve kalitesi, stres seviyesi, fiziksel aktivite ve üretkenlik gibi değişkenler yer almaktadır. Veriler ön işleme sürecinden geçirilmiş, eksik değerler medyan ile doldurulmuş, kategorik değişkenler sayısallaştırılmış ve tüm özellikler standardize edilmiştir. Ardından veri seti %80 eğitim ve %20 test olarak ayrılmıştır. Sınıflandırma için dört farklı model uygulanmıştır: Çok Katmanlı Algılayıcı (MLP), Uzun Kısa Süreli Bellek (LSTM), Autoencoder+MLP ve Karar Ağaçları+MLP. Modeller doğruluk, kesinlik, duyarlılık, F1 skoru ve ROC eğrileri ile değerlendirilmiştir. Bulgular, Karar Ağaçları+MLP modelinin %90 doğruluk, %92 kesinlik, %85 duyarlılık ve %88 F1 skoru ile en yüksek performansı sergilediğini göstermiştir. Özellikle “Kronik” ruh sağlığı sınıfında diğer modellerin ayrım gücü düşük kalırken, bu hibrit model sınıflar arası dengeli ve başarılı bir sınıflandırma sağlamıştır. Sonuç olarak, dijital davranış kalıpları ve yaşam tarzı göstergeleri ruh sağlığı durumlarını anlamada etkili değişkenlerdir ve yapay zeka tabanlı modeller bu ilişkileri yüksek doğrulukla ortaya koyabilmektedir.

Anahtar Kelimeler

• Yaşam tarzı
• teknoloji kullanımı
• ruh sağlığı
• derin öğrenme
• sınıflandırma

Kaynakça

1. Ahmad, I. (2019). Life style and health education. Gomal Journal of Medical Sciences, 17(3), 63–64. https://doi.org/10.46903/gjms/17.03.2079
2. Asian, J., Rosita, M. D., & Mantoro, T. (2022). Sentiment analysis for the Brazilian anesthesiologist using multi-layer perceptron classifier and random forest methods. Jurnal Online Informatika, 7(1), 132–141. https://doi.org/10.15575/join.v7i1.900
3. Asni, M. L. H. M., Zukhi, M. Z. M., Mat, D. M., & Muhammad, M. H. (2025). Leveraging machine learning for early detection of mental health issues among higher education students. Journal of Information System and Technology Management, 10(38), 119–133. https://doi.org/10.35631/JISTM.1038008
4. Azar, A. T., & El-Metwally, S. M. (2013). Decision tree classifiers for automated medical diagnosis. Neural Computing and Applications, 23(8), 2387–2403. https://doi.org/10.1007/s00521-012-1196-7
5. Balhara, S., & Nitin. (2024). Influence of smartphone addiction on mental health: A comprehensive review. International Journal of Progressive Research in Engineering Management and Science, 4(3), 578–582. https://doi.org/10.58257/IJPREMS32965
6. Bhavani, B. H., & Naveen, N. C. (2024). An approach to determine and categorize mental health condition using machine learning and deep learning models. Engineering, Technology & Applied Science Research, 14(2), 13780–13786. https://doi.org/10.48084/etasr.7162
7. Castellani, M. (2018). Competitive co-evolution of multi-layer perceptron classifiers. Soft Computing, 22(11), 3417–3432. https://doi.org/10.1007/s00500-017-2587-6
8. Cheng, J. P., & Haw, S. C. (2023). Mental health problems prediction using machine learning techniques. International Journal on Robotics, Automation and Sciences, 5(2), 59–72. https://doi.org/10.33093/ijoras.2023.5.2.7

9. Chung, J., & Teo, J. (2023). Single classifier vs. ensemble machine learning approaches for mental health prediction. Brain Informatics, 10(1), 1–6. https://doi.org/10.1186/s40708-022-00180-6
10. Dao, T. V., Sato, H., & Kubo, M. (2018). MLP-Mixer-Autoencoder: A lightweight ensemble architecture for malware classification. Information, 14(3), 1–14. https://doi.org/10.3390/info14030167
11. Dhariwa, N., Sengupta, N., Madiajagan, M., Patro, K. K., Kumari, P. L., Abdel Samee, N., Tadeusiewicz, R., Pławiak, P., & Prakash, A. J. (2024). A pilot study on AI-driven approaches for classification of mental health disorders. Frontiers in Human Neuroscience, 18, 1–17. https://doi.org/10.3389/fnhum.2024.1376338
12. Garg, K., Garg, S., Dixit, H., & Pandey, K. (2024). Machine learning driven analysis of mental health indicators in social media posts. In Proceedings of the 2024 5th International Conference on Electronics and Sustainable Communication Systems (ICESC) (pp. 1056–1062). IEEE. https://doi.org/10.1109/ICESC60852.2024.10689856
13. Gary, W. S., Jooyeon, L., Aaron, K., Jason, J., Prabha, S., Himaja, G., Teena, D. M., & Susan, Y. B. (2020). Brain health consequences of digital technology use. Dialogues in Clinical Neuroscience, 22(2), 179–187. https://doi.org/10.31887/DCNS.2020.22.2/gsmall
14. Govindaraj, M., Asha, V., Jayanth, H., Harshitha, D. G., Patil, H. V., & Devi, N. M. (2025). Mental health prediction using machine learning. In Proceedings of the 2025 International Conference on Intelligent Computing and Control Systems (ICICCS) (pp. 985–988). IEEE. https://doi.org/10.1109/ICICCS65191.2025.10984637
15. Hoque, A. S. M. M. (2018). Digital device addiction effect on lifestyle of generation Z in Bangladesh. Asian People Journal, 1(2), 21–44. https://journal.unisza.edu.my/apj/index.php/apj/article/view/68
16. Hossain, E., Alazeb, A., Mudawi, N. A., Almakdi, S., Alshehri, M., Faruque, M. G. G., & Rahman, W. (2022). Forecasting mental stress using machine learning algorithms. Computers, Materials & Continua, 72(3), 4945–4966. https://doi.org/10.32604/cmc.2022.027058
17. Huang, Z. (2025). Prediction of mental problem based on deep learning models. In Proceedings of the 3rd International Conference on Software Engineering and Machine Learning (pp. 56–63). https://doi.org/10.54254/2755-2721/138/2025.21185
18. Jain, T., Jain, A., Hada, P. S., Kumar, H., Verma, V. K., & Patni, A. (2021). Machine learning techniques for prediction of mental health. In Proceedings of the 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA) (pp. 1606–1613). IEEE. https://doi.org/10.1109/ICIRCA51532.2021.9545061
19. Kashyap, P., Jaiswal, A., Naithani, A., Aeri, M., & Dhondiyal, S. (2024). EmoSupport: A comparative study for the analysis of mental health of undergraduate students. In Proceedings of the 2024 2nd International Conference on Disruptive Technologies (ICDT) (pp. 470–481). IEEE. https://doi.org/10.1109/ICDT61202.2024.10489128
20. Lin, C. H., Chen, S. K., Chang, S. M., & Lin, S. S. J. (2013). Cross-lagged relationships between problematic Internet use and lifestyle changes. Computers in Human Behavior, 29(6), 2615–2621. https://doi.org/10.1016/j.chb.2013.06.029
21. Magomedova, A., & Fatima, G. (2025). Mental health and well-being in the modern era: A comprehensive review of challenges and interventions. Cureus, 17(1), 1–16. https://doi.org/10.7759/cureus.77683
22. Malave, S., Khemani, B., Kelkar, R., Balekundri, U., Bogar, S., & Kolekar, A. (2025). Improving mental health diagnosis with hybrid ensemble models: A data-driven approach. EPJ Web of Conferences, 328(01036), 1–15. https://doi.org/10.1051/epjconf/202532801036
23. Mandal, K. P., Chakraborty, R., Mondal, S. S., Karmakar, S., & Kundu, A. (2025). A comprehensive study: Mental health status prediction using machine learning. International Journal of Scientific Research in Engineering and Management, 9(6), 1–10. https://doi.org/10.55041/IJSREM50947
24. Nair, A., Yadav, N., Thawait, D., Tapre, S., Kashyap, S., Rathod, A., & Dhande, N. (2020). Gadgets: Its use and stress on lifestyle. Journal of Datta Meghe Institute of Medical Sciences University, 15(3), 183–187. https://doi.org/10.4103/jdmimsu.jdmimsu_37_20
25. Naveen, P. E., & Sujitha, J. (2023). Comparative analysis of machine learning techniques for mental health prediction. In Proceedings of the 2023 8th International Conference on Communication and Electronics Systems (ICCES) (pp. 1–6). IEEE. https://doi.org/10.1109/ICCES57224.2023.10192763
26. Nooruldeen, O. I., & Savaş, S. (2024). Sosyal medya etkileşimlerinde depresyonu tanımlamak için derin öğrenme tekniklerinin kullanılması. Sinop Üniversitesi Fen Bilimleri Dergisi, 9(2), 449–466. https://doi.org/10.33484/sinopfbd.1456956
27. Ogugua, J. O., Okongwu, C. C., Akomolafe, O. O., Anyanwu, E. C., & Daraojimba, O. D. (2024). Mental health and digital technology: A public health review of current trends and responses. International Medical Science Research Journal, 4(2), 108–125. https://doi.org/10.51594/imsrj.v4i2.754
28. Perera, T. D. M., Rupasingha, R. A. H. M., & Kumara, B. T. G. S. (2024). Deep learning-based ensemble model for predicting the lifestyle status of a person. In Proceedings of the 2024 4th International Conference on Advanced Research in Computing (ICARC) (pp. 25–30). IEEE. https://doi.org/10.1109/ICARC61713.2024.10499747
29. Priya, A., Garg, S., & Tigga, N. P. (2020). Predicting anxiety, depression and stress in modern life using machine learning algorithms. Procedia Computer Science, 167, 1258–1267. https://doi.org/10.1016/j.procs.2020.03.442
30. Rajak, S., & Baruah, U. (2025). A novel ensemble of convolutional neural network with decision tree classifier for hostile post detection in Hindi. International Journal of Information Technology, 27(1), 1–12. https://doi.org/10.1007/s41870-025-02424-0
31. Sharma, E., & Gupta, S. (2024). Exploring the impact of technology use on the mental health of teacher trainees. International Journal for Multidisciplinary Research, 6(6), 1–6. https://doi.org/10.36948/ijfmr.2024.v06i06.34205
32. Shetty, K., Sanjana, Savitha, Murthy, A., Harshitha, G. M., & Prathwini. (2025). Assessing university students’ mental health through ensemble machine learning: The role of academic, social, and lifestyle factors. In Proceedings of the 2025 International Conference on Artificial Intelligence and Data Engineering (AIDE) (pp. 650–658). IEEE. https://doi.org/10.1109/AIDE64228.2025.10987514
33. Shrivastav, S., Garg, K., Bala, K., & Kumar, Y. (2024). Enhancing sleep health and lifestyle using machine learning-based approaches. In Proceedings of the 2024 International Conference on Artificial Intelligence and Emerging Technology (pp. 36–41). IEEE. https://doi.org/10.1109/GLOBALAISUMMIT62156.2024.10947869
34. Singh, G., & Gill, K. S. (2024). Mental health analytics: A comparative exploration of machine learning models. In Proceedings of the 2024 International Conference on Intelligent Computing and Emerging Communication Technologies (ICEC) (pp. 1–5). IEEE. https://doi.org/10.1109/ICEC59683.2024.10837048
35. Spytska, L. (2025). Digital technology and mental health: Unveiling the psychological impact of modern digital habits. Jurnal Ilmiah Ilmu Terapan Universitas Jambi, 9(1), 348–365. https://doi.org/10.22437/jiituj.v9i1.38238
36. Srividya, M., Mohanavalli, S., & Bhalaji, N. (2018). Behavioral modeling for mental health using machine learning algorithms. Journal of Medical Systems, 42(88), 1–6. https://doi.org/10.1007/s10916-018-0934-5
37. Tamang, M. T., Sharif, S., & Ghorashi, S. A. (2025). Transforming mental health assessment: Machine learning for early detection and personalized care among college students. Human Interaction and Emerging Technologies, 196, 123–133. https://doi.org/10.54941/ahfe1005961
38. Temiz, N. (2023). Bilgi ve iletişim teknolojilerinde yaşanan gelişmelerin insan sağlığı üzerindeki etkileri. Adıyaman Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 16(44), 539–562. https://doi.org/10.14520/Adyusbd.1311164
39. Turel, O., Serenko, A., & Giles, P. (2011). Integrating technology addiction and use: An empirical investigation of online auction users. MIS Quarterly, 35(4), 1043–1061. https://doi.org/10.2307/41409972
40. Uslu, O. (2022). Causes and consequences of technology addiction: A review of information systems and information technology studies. International Journal of Social Sciences and Education Research, 8(3), 299–306. https://doi.org/10.24289/ijsser.1131136
41. Yang, Z. (2024). Competing leaders grey wolf optimizer and its application for training multilayer perceptron classifier. Expert Systems with Applications, 239, 1–19. https://doi.org/10.1016/j.eswa.2023.122349
42. Yuan, S., Wu, X., & Xiang, Y. (2018). Incorporating pre-training in long short-term memory networks for tweet classification. Social Network Analysis and Mining, 8(52), 1–16. https://doi.org/10.1007/s13278-018-0530-1
43. Zhang, L., Zhao, S., Yang, Z., Zheng, H., & Lei, M. (2024). An artificial intelligence platform to stratify the risk of experiencing sleep disturbance in university students. Psychology Research and Behavior Management, 17, 1057–1071. https://doi.org/10.2147/PRBM.S448698
44. Zhang, S., Zheng, D., Hu, X., & Yang, M. (2015). Bidirectional long short-term memory networks for relation classification. In Proceedings of the 29th Pacific Asia Conference on Language, Information and Computation (pp. 73–78). Association for Computational Linguistics. https://aclanthology.org/Y15-1009/