EXPOSING INAUTHENTIC SOCIAL MEDIA PROFILES

The system developed to Expose Inauthentic Social Media Profiles is a very strong capability of automated learning, digital forensics, and behavioural analytics in the identification of suspicious online accounts with high accuracy. Analysis of profile metadata, evaluation of patterns of engagements, verification of images, and activity behaviour provide surefire ways of identifying accounts that are fake, driven by bots, or impersonated across various social media platforms. Unlike traditional manual verification methods, which are time-consuming and prone to human error, this automated solution offers faster, more consistent, and transparent results. This was designed to work even when profiles attempt to mask inauthentic behaviour through artificial engagement, odd posting behaviours, or stolen digital identities.   Once analyses of data are performed, this system performs its efficiency on uneven grounds-be it varying levels of interaction, or inconsistent content patterns, or sudden spikes in followers-but proves to be adaptable and suitable for fields ranging from cybersecurity and digital marketing to law enforcement agencies and educational institutes, where the documentation of bogus profiles is quite necessary for a trustful and safe environment.   The project, therefore, testifies to the growing importance of automated social media authentication in a modern digital world that faces such serious problems as online misinformation, identity theft, and manipulation driven by bots. It allows for the precise detection of suspicious profiles, hence creating safer online environments and reducing human effort in monitoring harmful activities.

1.  Cao, Q., et al. (2012). A large-scale analysis of networking sites. ACM Transactions on the Web (TWEB), 6(2), 6:1-6:37. 2.   Boshmaf, Y., et al. (2011). The social bot network: detection and measurement. 3.  Al-Hassan, M., et al. (2013). Sybil defence in social networks: a survey. Journal of Network and Computer Applications, 36(4), 1145-1153. 4.  Kudugunta, S., & Harish, B. (2018). Deep Bot: automated bot detection in social networks using deep learning. 5.  Yang, K. C., et al. (2019). Scalable and explainable bot detection in social networks. IEEE Access, 7, 132174-132185. 6.   Ferrara, E., et al. (2016). The rise of social bots. Communications of the ACM, 59(7), 96-104. 7.   Cresci, S., et al. (2017). DeBot: network-based detection of Twitter bots. In Proceedings of the 26th International Conference on World Wide Web (WWW '17), pp. 1061-1069. 8.   Grimm, J., et al. (2020). Linguistic Markers of Bots and Automated Content in Social Media. In Proceedings of the International Conference on Computational Linguistics (COLING), pp. 5898-5909. 9.  Piskorski, J., et al. (2018). Distinguishing between human and automated Twitter accounts using deep text representations.