Social Media Addiction and Relationship Impact Analysis System

Abstract

Social media platforms have become an integral part of modern communication, enabling users to interact, share information, and maintain social connections. However, excessive usage of social media has emerged as a growing concern, often leading to behavioral addiction that negatively influences emotional well-being and interpersonal relationships. This project proposes a Social Media Addiction and Relationship Impact Analysis System that utilizes machine learning techniques to identify addiction levels and analyze their impact on relationship quality. The system collects user behavioral data such as daily usage duration, login frequency, late-night activity, and interaction patterns along with relationship indicators including communication frequency, emotional support level, and satisfaction score. The collected data is processed using preprocessing techniques and analyzed using the Random Forest classification algorithm to categorize addiction levels into Low, Moderate, and High. The system further evaluates how these addiction levels affect communication quality, trust, and emotional bonding in relationships. Experimental results demonstrate that the proposed system effectively detects addiction patterns and predicts relationship impact with high accuracy. The system also provides visualization dashboards and recommendations to promote awareness and help users maintain healthy digital habits.

Introduction

The text explores how excessive use of social media platforms like Facebook, Instagram, and Twitter can lead to social media addiction, negatively affecting psychological well-being and interpersonal relationships. Overuse often reduces real-life communication, leading to issues such as emotional neglect, conflicts, and lower relationship satisfaction.

Traditional studies rely on surveys and manual analysis, which are time-consuming and prone to bias. To overcome this, the proposed system uses data analytics and machine learning to automatically detect addiction levels and analyze their impact on relationships, including factors like communication quality, emotional bonding, and conflict frequency.

The literature review shows that social media addiction is linked to emotional problems such as loneliness, anxiety, and jealousy. While machine learning techniques (e.g., Decision Trees, SVM, Random Forest) are effective in behavioral analysis, existing systems lack integrated solutions combining addiction detection and relationship impact analysis.

The proposed methodology includes:

• Data collection (usage patterns, emotional and relationship indicators)
• Data preprocessing (cleaning, normalization)
• Feature extraction and model training
• Classification of addiction levels and relationship impact
• Visualization through dashboards

Overall, the system provides automated insights to help users, researchers, and counselors understand the effects of social media usage and take steps to maintain healthier relationships.

Conclusion

This research presented a Social Media Addiction and Relationship Impact Analysis System that utilizes machine learning techniques to detect addiction levels and analyze their influence on relationships. The system integrates data preprocessing, feature extraction, Random Forest classification, and visualization to provide comprehensive behavioral insights. Experimental results show that the system can accurately classify addiction levels and identify their impact on relationship quality. The system also helps in early detection of risky behavioral patterns and supports awareness about responsible social media usage. Future improvements may include integrating real-time data from social media platforms, implementing deep learning models, and developing mobile-based wellness applications.

References

[1] Andreassen, C. S., et al. (2016). The relationship between addictive use of social media and psychological disorders. [2] Kross, E., et al. (2013). Facebook use predicts declines in subjective well-being. PLOS ONE. [3] Griffiths, M. D. (2012). Social networking addiction: Emerging behavioral addiction. [4] Han, B., et al. (2022). Social media addiction and its impact on relationships. [5] Breiman, L. (2001). Random Forests. Machine Learning Journal.

Copyright

Copyright © 2026 Ms. T. Princess Raichel, Padigala Dwaraka , Palagiri Vedhitha, Palagiri Asif, Palyam Thowhid, Padigepati Sudheer Kumar Reddy. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.