LIES GONE VIRAL – DETECTION AND ANALYSIS OF TELUGU FAKE NEWS USING MACHINE LEARNING ALGORITHMS

The current study provides various directions that are important to explore further in order to advance fake news detection. First, multimodal models should be investigated in depth as they allow processing textual and visual content together since misinformation might include not only text but also images or other multimedia components to add more credibility to misleading statements. Second, multilingual and cross-cultural models for fake news detection must be explored because there are some low-resource languages that might require the development of specific solutions for detecting fake news. Multilingual and cross-cultural approaches may allow building models that would have high generalization capabilities due to the use of transfer learning strategies. Third, adversarial robustness must be considered as it will ensure that detection models can deal with manipulated or adversarial data without being fooled. Moreover, temporal adaptation mechanisms such as continual or online learning might provide opportunities for developing detection models that could cope with evolving patterns in fake news. Finally, explainability of fake news detection models is one more issue to be addressed as it will allow making predictions easier to understand and interpret by people.

[1] K. Shu, A. Sliva, S. Wang, J. Tang, and H. Liu, “Fake News Detection on Social Media: A Data Mining Perspective,” ACM SIGKDD Explorations, vol. 19, no. 1, pp. 22–36, 2017. [2] H. Allcott and M. Gentzkow, “Social Media and Fake News in the 2016 Elec- tion,” Journal of Economic Perspectives, vol. 31, no. 2, pp. 211–236, 2017. [3] H. Ahmed, I. Traore, and S. Saad, “Detection of Online Fake News Using N- gram Analysis and Machine Learning Techniques,” International Conference on Intelligent, Secure, and Dependable Systems, 2017. [4] A. Bondielli and F. Marcelloni, “A Survey on Fake News and Rumour Detec- tion Techniques,” Information Sciences, vol. 497, pp. 38–55, 2019. [5] B. Guo, Y. Ding, L. Yao, Y. Liang, and Z. Yu, “The Future of False Information Detection on Social Media: New Perspectives and Trends,” ACM Computing Surveys, vol. 53, no. 4, pp. 1–36, 2020. [6] T. Joachims, “Text Categorization with Support Vector Machines: Learning with Many Relevant Features,” European Conference on Machine Learning (ECML), 1998. [7] G. Salton and C. Buckley, “Term-weighting approaches in automatic text re- trieval,” Information Processing & Management, vol. 24, no. 5, pp. 513–523, 1988. [8] S. B. Parikh and P. K. Atrey, “Media-Rich Fake News Detection: A Sur- vey,” IEEE Conference on Multimedia Information Processing and Retrieval (MIPR), 2018. [9] P. Atanasova, D. Wright, and I. Augenstein, “Generating Label Cohesive and Well-Formed Adversarial Claims,” Proceedings of the 2020 Conference on Em- pirical Methods in Natural Language Processing (EMNLP), pp. 3034–3050, 2020. [10] R. Baly, G. Karadzhov, D. Alexandrov, J. Glass, and P. Nakov, “Predict- ing Factuality of Reporting and Bias of News Media Sources,” Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 3528–3539, 2018. [11] K. S. Hasan and V. Ng, “Stance Classification of Ideological Debates: Data, Models, Features, and Constraints,” in Proc. IJCNLP, 2013, pp. 1348–1356.