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{195042,
        author = {B.Vaishnavi and K.Jyothi and M.Medhasri and M.Manasa and R.Mounika},
        title = {vA Graph-Based Deep Learning Approach for Fake Profile and Botnet Detection in Social Media Networks},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {5891-5899},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195042},
        abstract = {Graph Neural Networks (GNNs) offer a powerful approach to social network analysis, particularly for identifying fake profiles and botnets prevalent on Indian platforms like Twitter, Facebook, and WhatsApp. This study develops a GNN-based model tailored to India's diverse digital landscape, leveraging graph structures to capture user connections, interaction patterns, and behavioral signals for enhanced detection accuracy. The methodology processes real-world datasets from Indian social media, incorporating features like follower graphs, posting frequency, content sentiment, and network centrality, while addressing challenges such as multilingual text and rapid bot evolution. Experimental results demonstrate superior performance over traditional ML methods, achieving up to 95% precision in fake profile detection and 92% for botnet clustering, enabling platforms to mitigate misinformation and cyber threats effectively.},
        keywords = {Graph Neural Networks, Social Graph Analytics, Fake Account Spotting, Bot Cluster Detection, Indian Online Networks, Link Embeddings, User Behavior Analysis, Local Language Processing, Fake Info Prevention, Next-Gen GNN Techniques.},
        month = {March},
        }