As social media and content-sharing platforms have evolved; misinformation and fake news have spread like wildfire, leading people to believe harmful misinformation. In this way, they can influence public opinion, spread fear, and drive people insane. Fake news identification is a current area of research aimed at determining whether content is genuine. In addition, this has significantly increased the daily amount of information on the Internet. Information can go viral in a matter of seconds thanks to social media, which has changed the way we share and process news. Everyone now relies on many online news sources because the internet is so widely used. News quickly disseminated across millions of users in a very short period of time along with the increase in the use of social media platforms like Facebook, Twitter, etc. The spread of fake news has far-reaching effects, including the formation of skewed beliefs and the manipulation of election results in favour of particular politicians. Moreover, spammers utilise alluring news headlines as click-bait for their adverts in order to make money. To provide more accurate predictions, RCNN models are trained to identify language-driven features according to content properties. This model addresses this using an efficient feature selection method.
Keywords: Machine learning, RCNN, Fake news, Social media, Language-driven features.
[1] C. Castillo, M. Mendoza, et al. (2013). Forecasting information credibility in time-sensitive social media. Internet Research, 23(5): 560–588.
[2] T. Chen, L. Wu, X. Li, J. Zhang, H. Yin, & Y. Wang (2017). Call attention to rumours: Deep attention-based recurrent neural networks for rumour detection in the early stages. Preprint ArXiv:1704.05973.
[3] Z.-Y. Liu, Y.-C. Chen, and H.-Y. Kao (2017). Convolutional neural networks for stance identification and rumour verification at several-2017 task 8 is something Ikm is working on. Sem Eval Proceedings, ACL.
[4] I. Augenstein, A. Vlachos, & K. Bontcheva (2016). Usfd at semeval-2016 task 6: Any-target stance detection on Twitter with autoencoders. In Sem Eval@NAACL-HLT, Pages 389–393.
[5] S.B. Doug Sibley & Yuxia Pan Talos (2016). Available online at http://blog.talosintelligence.com.
[6] B.S. Andreas Hanselowski, Avinesh PVS., & F. Caspelherr (2017). Team athene on the fake news challenge.
[7] Bahad, P., Saxena, P., & Kamal, R. (2019). Fake News Detection using Bi-directional LSTM-Recurrent Neural Network. Procedia Computer Science, 165: 74–82.
[8] Wang, Y., Ma, F., Jin, Z., Yuan, Y., Xun, G., Jha, K., Su, L., & Gao, J. (2018). EANN. In Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. KDD ’18: The 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.
[9] Kai Shu, et al. (n.d). Fake News Detection on Social Media: A Data Mining Perspective.
[10] Ruchansky, N., Seo, S., & Liu, Y. (2017). CSI: A Hybrid Deep Model for Fake News Detection. arXiv. doi: https://doi.org/10.48550/ARXIV.1703.06959.
[11] Conroy, N.K., Rubin, V.L., & Chen, Y. (2015). Automatic deception detection: Methods for finding fake news. In Proceedings of the Association for Information Science and Technology, 52(1): 1–4.
[12] J. D'Souza (2018). An Introduction to Bag-of-Words in NLP. Available:https://medium.com/greyatom/an- introduction-tobag-of-words-in-nlp-ac967d43b428.
[13] G. Bonaccorso (2017). Artificial Intelligence, Machine Learning, and Data Science. Available: https://www. bonaccorso.eu/2017/10/06/mlalgorithms-addendum-passive-aggressivealgorithm.
Source of Funding:
This study did not receive any grant from funding agencies in the public or not-for-profit sectors.
Competing Interests Statement:
The authors have declared no competing interests.
Consent for Publication:
The authors declare that they consented to the publication of this study.
Authors’ Contribution:
Both the authors took part in literature review, research, and manuscript writing equally.
