Abstract: With the COVID-19 pandemic and other global conflicts taking over the media, the rapid dissemination of misinformation online has drawn attention to the problem of fake news. Fake news can have detrimental effects, as demonstrated by the impact of the online anti-masking advocacy in exacerbating the COVID-19 pandemic. Various solutions have been proposed regarding the detection of fake news, with one of the most promising being deep learning. This study aims to advance current deep learning solutions in the field of fake news detection with the development of a CNN-RNN (convolutional neural network-recurrent neural network) with a complementary URL classifier. In constructing the fake news classifier, datasets were run through pre-processing techniques before being used for training. The model was subsequently tested on three datasets, spanning different areas of news: ISOT (general news), ReCOVery (COVID-19 news), and FA-KES (Syrian war news). A user interface additionally facilitated public access to the fake news classifier. After training the model on the ISOT and ReCOVery datasets, the model was able to achieve overall testing accuracies of 0.9898 (ISOT), 0.8466 (ReCOVery), and 0.5441 (FA-KES). Overall, this study broadens the options with which fake news can be identified.
Keywords – CNN-RNN (convolutional neural network-recurrent neural network), deep learning, fake news, ISOT, FA-KES, ReCOVery, UI (user interface)
Ahmed H, Traore I, Saad S. “Detecting opinion spams and fake news using text classification”, Journal of Security and Privacy, Volume 1, Issue 1, Wiley, January/February 2018.
Ahmed H, Traore I, Saad S. (2017) “Detection of Online Fake News Using N-Gram Analysis and Machine Learning Techniques. In: Traore I., Woungang I., Awad A. (eds) Intelligent, Secure, and Dependable Systems in Distributed and Cloud Environments. ISDDC 2017. Lecture Notes in Computer Science, vol 10618. Springer, Cham (pp. 127- 138).
BBC. (2020, May 24). Coronavirus: Which health claims are circulating online? BBC News.
Buchanan, T., & Benson, V. (2019). Spreading disinformation on Facebook: do trust in message source, risk propensity, or personality affect the organic reach of “fake news”?. Social media+ society, 5(4), 2056305119888654.
Desai, S., Mooney, H., & Oehrli, J. A. (2020). Research guides:“fake news,” lies and propaganda: how to sort fact from fiction: what is “fake news”. Michigan University.
Elhadad, M. K., Li, K. F., & Gebali, F. (2019, November). A novel approach for selecting hybrid features from online news textual metadata for fake news detection. In International Conference on P2P, Parallel, Grid, Cloud and Internet Computing (pp. 914-925). Springer, Cham.
Gottfried, J. (2020). Around three-in-ten Americans are very confident they could fact-check news about COVID-19. Pew Research Center.
Jain, A. K., & Gupta, B. B. (2018). PHISH-SAFE: URL features-based phishing detection system using machine learning. In Cyber Security (pp. 467-474). Springer, Singapore.
Mazzeo, V., Rapisarda, A., & Giuffrida, G. (2021). Detection of Fake News on COVID-19 on Web Search Engines. Frontiers in Physics, 9.
Newberry, C. (2022, February 28). How the Facebook algorithm works in 2022. Hootsuite.
Salem, F. K. A., Al Feel, R., Elbassuoni, S., Jaber, M., & Farah, M. (2019, July). Fa-kes: A fake news dataset around the syrian war. In Proceedings of the International AAAI Conference on Web and Social Media (Vol. 13, pp. 573-582).
Sample, C., Jensen, M. J., Scott, K., McAlaney, J., Fitchpatrick, S., Brockinton, A., ... & Ormrod, A. (2020). Interdisciplinary lessons learned while researching fake news. Frontiers in Psychology, 2947.
Snopes media bias rating. AllSides. (2021, August 18).