Copyright © 2026 Authors retain the copyright of this article. This article 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.

@article{189230,
        author = {DEVARAJA H M and DHEERAJ S and CHANDRASHEKAR J H M and KARTHIK E and NAGA ASHWINI NAYAK V J},
        title = {FAKE SOCIAL MEDIA ACCOUNTS AND THEIR DETECTION},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {6049-6054},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=189230},
        abstract = {social media has become one of the most influential communication platforms in the digital age, enabling users to interact, share content, and form online communities. However, the rapid growth of these platforms has also resulted in a significant rise in fake accounts, bots, and impersonation profiles. These fraudulent accounts are commonly used to spread misinformation, manipulate public opinion, conduct online fraud, and violate user privacy, posing serious challenges to digital trust and online security. Traditional manual methods for detecting fake profiles are time-consuming, inefficient, and unsuitable for handling large-scale social media data. 
In this paper, a machine learning-based Fake Social Media Account Detection System is proposed to automatically classify social media accounts as real or fake. The system analyzes various features such as behavioral patterns, profile attributes, follower–following ratios, posting frequency, and engagement activities. Machine learning models are developed and trained using Python-based libraries including TensorFlow and Scikit-learn. The trained model is integrated into a Flask-based web application to provide real-time detection through a simple and user-friendly interface. Experimental results demonstrate that the proposed system achieves high accuracy and reliability in terms of precision, recall, and F1-score. The proposed approach enhances digital authenticity, reduces the spread of misinformation, and contributes to creating safer and more secure online social networks},
        keywords = {Fake Social Media Accounts, Machine Learning, Behavioral Analysis, Social Media Security, Classification, Cybersecurity},
        month = {December},
        }