ARTIFICIAL INTELLIGENCE FOR DETECTING ALGORITHMIC MANIPULATION IN SOCIAL MEDIA

This paper presented a comprehensive investigation into the application of Artificial Intelligence for detecting algorithmic manipulation in social media platforms. The proposed multi-layered framework integrates behavioral profiling, content-based feature extraction, network topology analysis, and deep learning classification to deliver a robust and scalable detection solution. Comparative evaluation across multiple model configurations demonstrates that the proposed ensemble approach achieves state-of-the-art performance, with an accuracy of 97.3% and F1-score of 96.5% on benchmark datasets. The paper further advanced the field through systematic discussions of multimodal analysis for cross-modality deepfake detection, Explainable AI techniques for transparent decision-making, adversarial defense mechanisms for long-term system resilience, and ethical frameworks for responsible deployment. These contributions collectively address the full lifecycle of an operationally viable manipulation detection system, from data ingestion to actionable output generation. As social media platforms continue to evolve as primary information channels in modern societies, the imperative for robust, adaptive, and ethically grounded detection systems will only intensify. The convergence of advances in AI, distributed computing, and regulatory governance creates a uniquely promising opportunity to significantly curtail the detrimental influence of algorithmic manipulation on global information ecosystems.  Future  work  will  focus  on  real-time federated detection across platforms, self-supervised learning for low-resource detection scenarios, and causal modeling of manipulation propagation dynamics.

[1]  E. Ferrara, O. Varol, C. Davis, F. Menczer, and A. Flammini, "The rise of social bots," Communications of the ACM, vol. 59, no. 7, pp. 96–104, July 2016. [2]  K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, "Fake news detection on social media: A data mining perspective," ACM SIGKDD Explorations Newsletter, vol. 19, no. 1, pp. 22–36, Sept. 2017. [3]  C. Shao, G. L. Ciampaglia, O. Varol, K. Yang, A. Flammini, and F. Menczer, "The spread of low-credibility content by social bots," Nature Communications, vol. 9, art. no. 4787, Nov. 2018. [4]  Y. Mirsky and W. Lee, "The creation and detection of deepfakes: A survey," ACM Computing Surveys, vol. 54, no. 1, pp. 1–41, Jan. 2021. [5]  S. Cresci, R. Di Pietro, M. Petrocchi, A. Spognardi, and M. Tesconi, "The paradigm-shift of social spambots: Evidence, theories, and tools for the arms race," Proc. WWW Companion, pp. 963–972, Apr. 2017. [6]  V. S. Subrahmanian et al., "The DARPA Twitter bot challenge," Computer, vol. 49, no. 6, pp. 38–46, June 2016. [7]  N. Hassan, B. Adjeroh, and M. Elmaghraby, "Deep learning models for malicious bot detection in social media," IEEE Access, vol. 8, pp. 11234–11245, Feb. 2020. [8]  T. T. Nguyen et al., "Deep learning for deepfakes creation and detection: A survey," Computer Vision and Image Understanding, vol. 196, pp. 1029–1042, July 2020. [9]  H. Guo et al., "Rumor detection with hierarchical social attention network," Proc. CIKM, pp. 943–951, Oct. 2018. [10]  M. Heidari, M. Jones, and O. Uzuner, "Deep learning models for detecting algorithmic manipulation on Twitter," IEEE Trans. Computational Social Systems, vol. 8, no. 1, pp. 124–135, Mar. 2021.