A Review on Machine Learning driven Analysis of Internet and Social Media Addiction and its Influence on Academic Outcome and Cybercrime

Authors

  • Abhendra Pratap Singh Author
  • Nandini Sharma Author
  • Saksham Goyal Author
  • Yatharth Author
  • Bhavya Pratap HMRITM, Hamidpur, New Delhi, 110036, Delhi, India Author

Abstract

The paper investigates the usage of Machine Learning for analysing the factors driving internet and social media addiction to understand their societal impacts. As the internet is being used everywhere now, it's crucial for everyone to understand how digital technology works, affects school performance, and cybercrimes, allowing one to create better protective measures. It examines the utilization of advanced predictive models like Random Forests and Neural Networks for measuring user's screen-time, psychological indicators, and educational records on a large scale. By collecting data through the identification of patterns that traditional statistical methods might overlook, the ML models categorized the level of dependency and correlated them with specific outcomes. This paper also analysed the academic impact on students due to the high level of online addiction on scrolling reels, playing games, and many more, which leads to decrement in marks or GPA. It also addresses the increase of cybercrime by users, lowering their barriers to cyber-deviance, either as a victim of phishing, harassment, or digital fraud. It provides a framework for educational institutions and law enforcement to predict high risk behaviours among the students utilizing various machine learning models. Users may use real time AI driven tools for supporting their productivity and wellness in the digital age.

References

[1] Bin Rofi, I., Eshita, M.M., Ahmed, M.S. and Noor, J., 2024, December. Identifying Influences: A Machine Learning and Explainable AI Approach to Analyzing Social Media Addiction Resulting from Academic Frustration. In Proceedings of the 11th International Conference on Networking, Systems, and Security (pp. 128-136).

[2] Mim, M.N., Firoz, M., Islam, M.M., Hasan, M. and Habib, M.T., 2024. A study on social media addiction analysis on the people of Bangladesh using machine learning algorithms. Bulletin of Electrical Engineering and Informatics, 13(5), pp.3493-3502.

[3] Hemal, S.H., Khan, M.A.R., Ahammad, I., Rahman, M., Khan, M.A.S.D. and Ejaz, S., 2024. Predicting the impact of internet usage on students’ academic performance using machine learning techniques in Bangladesh perspective. Social Network Analysis and Mining, 14(1), p.66.

[4] Hire, N., Patil, P., Nandwalkar, B., Mahale, D. and Patel, J., 2024. Cybercrimes on Social Media using Machine Learning. JOURNAL OF ELECTRICAL ENGINEERING (ISSN NO: 2095-9524), 9(5).

[5] Balakrishnan, V., Khan, S. and Arabnia, H.R., 2020. Improving cyberbullying detection using Twitter users’ psychological features and machine learning. Computers & Security, 90, p.101710.

[6] Nti, I.K., Akyeramfo-Sam, S., Bediako-Kyeremeh, B. and Agyemang, S., 2022. Prediction of social media effects on students’ academic performance using Machine Learning Algorithms (MLAs). Journal of Computers in Education, 9(2), pp.195-223.

[7] Mahat, M., 2021. Prediction and prevention of addiction to social media using machine learning. In Machine Learning and Information Processing: Proceedings of ICMLIP 2020 (pp. 319-329). Singapore: Springer Singapore.

[8] Klochko, O.V., Fedorets, V.M., Klochko, V.I. and Kormer, M.V., 2022. The Use of Ensemble Classification and Clustering Methods of Machine Learning in the Study of Internet Addiction of Students. In Proceedings of the 1st Symposium on Advances in Educational Technology (Vol. 1, pp. 241-260).

[9] Lombo, X., Oyelade, O.N. and Ezugwu, A.E., 2022, July. Crime detection and analysis from social media messages using machine learning and natural language processing technique. In International Conference on Computational Science and Its Applications (pp. 502-517). Cham: Springer International Publishing.

[10] Parasar, A., Sujatha, N., Priya, S., Pramod, S., Kumar, A.S. and Palanimuthu, K., 2025, February. Machine learning-based detection of stress levels in students with social media addiction. In 2025 3rd International Conference on Integrated Circuits and Communication Systems (ICICACS) (pp. 1-6). IEEE.

[11] Ohu, F.C. and Jones, L.A., 2025, February. AI-driven forensic cyberpsychology intervention strategies for social media platform and school managers to mitigate cyber fraud at-risk adolescents. In Scientia Moralitas Conference Proceedings (pp. 114-131).

[12] Wahed, S.A. and Wahed, M.A., 2025. AI-Driven Digital Well-being: Developing Machine Learning Model to Predict and Mitigate Internet Addiction. LatIA, (3), p.73.

[13] Hosseini, M., Parsarad, S. and Amirjani, F., 2025, August. Behavior-Based Detection of Instagram Addiction Using Machine Learning: Accuracy and Privacy Implications. In International Conference on Availability, Reliability and Security (pp. 161-173). Cham: Springer Nature Switzerland.

[14] Ali, A., Hosain, M.S., Siddik, M.A.B., Hasan, M., Habib, M.A., Kabir, M.A., Rahman, M.M., Shanto, P.A., Hasan, N. and Mahmud, A., 2025. Classifying Internet Addiction Using Machine Learning Approach: A Study Among Adolescents in Bangladesh. Public Health Challenges, 4(4), p.e70165.

[15] Jaiswal, M., Manchattahalli, U.R., Devi, V.S. and Jacob, M.S., 2026, January. Predictive Analysis of Internet Use and Risk Among Children and Adolescents via Machine Learning. In 2026 Sixth International Conference on Advances in Electrical, Computing, Communications and Sustainable Technologies (ICAECT) (pp. 1-6). IEEE.

[16] Onah, C. and Ogwuche, C.H., 2024. Cybercrimes And Social Media Addictions: The Role Of Perceived Use Of Conversational GPT-4 AI Model Among Residents In Nigeria. Academic Journal of Psychology and Counseling, 5(2), pp.170-201.

[17] Vimala, S., 2025. Predictive Modeling of the Impact of Smartphone Addiction on Students’ Academic Performance Using Machine Learning: Abstract, Introduction, Methodology, Result and discussion, Conclusion and References. International Journal of Information Technology, Research and Applications, 4(3), pp.08-15.

[18] Wasid, M., Amar, A.Y.A., Ahmad, S. and Mustafa, J., 2025. Enhancing reliability and security in online social networks: intelligent learning models for cybercrime detection. Life Cycle Reliability and Safety Engineering, pp.1-17.

[19] Tegar, A.T.B.S., Hasanah, H. and Oktaviani, I., 2025. Predicting Social Media Addiction Using Machine Learning and Interactive Visualization with Streamlit. bit-Tech, 8(1), pp.778-788.

[20] Ibitoye, A.O., Ravindran, R., Afe, O.F. and Abiodun, A.O., 2025. Predicting and mitigating digital addiction with Machine Learning Models for improved mental health outcomes. Journal of Social Computing, 6(4), pp.359-377.

[21] Ibitoye, A.O., Ravindran, S., Afe, O.F. and Abiodun, A.O., 2025. Predicting Digital Addiction Patterns with Machine Learning for Personalised Mental Health Support. Journal of Social Computing, 6(4), pp.359-377.

[22] Elluri, L., Mandalapu, V., Vyas, P. and Roy, N., 2025. Recent advancements in machine learning for cybercrime prediction. Journal of Computer Information Systems, 65(2), pp.249-263.

Published

2026-09-21

Issue

Vol. 1 No. 1 (2026): Proceedings of the 4th International Conference on Emerging Applications of Artificial Intelligence, Machine Learning and Cybersecurity

Section

Articles

License

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.