Research Article
Unveiling the Underworld: Detecting Fake Profiles Through Network Analysis and Behavioral Modeling on Social Media
@INPROCEEDINGS{10.1007/978-3-031-66044-3_26, author={Bhrugumalla L. V. S. Aditya and Sachi Nandan Mohanty}, title={Unveiling the Underworld: Detecting Fake Profiles Through Network Analysis and Behavioral Modeling on Social Media}, proceedings={Pervasive Knowledge and Collective Intelligence on Web and Social Media. Second EAI International Conference, PerSOM 2023, Hyderabad, India, November 24--25, 2023, Proceedings}, proceedings_a={PERSOM}, year={2024}, month={8}, keywords={Typing Pattern Analysis Posting Behavior Friending Behavior Fake Profiles Network Analysis Behavioural Modeling Scenarios}, doi={10.1007/978-3-031-66044-3_26} }- Bhrugumalla L. V. S. Aditya
Sachi Nandan Mohanty
Year: 2024
Unveiling the Underworld: Detecting Fake Profiles Through Network Analysis and Behavioral Modeling on Social Media
PERSOM
Springer
DOI: 10.1007/978-3-031-66044-3_26
Abstract
Internet trust requires detecting fake social media profiles. This study proposes exposing bogus accounts using typing pattern analysis, posting conduct, and friending behavior. Network analysis and behavioral modeling identify and classify bogus profiles. This work is crucial as fake accounts spread misinformation, phishing, and scams. Fake accounts harm communities and businesses. Detecting fake profiles requires better methods. Typing, publishing, and friending patterns reveal fake accounts. Typing pattern research explores fake accounts’ increasing typo and grammatical errors. Posting habit analysis demonstrates high frequency and unrelated content. Examine rapid friend accumulation or relationships outside the user’s social circle. We analyze our method using a CNN classifier. Our experiments found fake accounts with 91.5% accuracy, 90.8% precision, and 92.5% recall. This study has several applications. Our solution improves fraud detection for social media networks to find and eliminate fake accounts. This prevents bogus news, scams, and user interactions. Our method helps users evaluate profile authenticity, enabling educated online judgments.
