COVIDFakeExplainer: An Explainable Machine Learning based Web Application: Conclusion & References

Table of Links

• Abstract & Introduction
• Related Works
• Materials and Methods
• Results and Discussion
• Conclusion & References

V. CONCLUSION

This paper presents a comprehensive pipeline encompassing the entire process, from training machine learning models to prototype implementation, for the detection of fake news with explainability. Our study demonstrates the potential of combining machine learning and explainability techniques to create a web application tailored for detecting COVID-19- related fake news. Through an extensive empirical analysis, we evaluated the performance of three prominent machine learning algorithms for text classification across seven distinct configurations, employing two distinct datasets. The results indicate that BERT emerges as the optimal choice for COVID19 fake news classification. Moreover, we critically examined the two leading explainability visualization techniques, offering insights into their respective advantages and limitations. Finally, we developed a prototype web application in the form of a Chrome extension. This approach is highly adaptable and can be extended beyond COVID-19 fake news detection, for instance, to classify text or misinformation in a variety of domains. The only requirement for this adaptation is the replacement of the model that serves as the foundation for the application.

In the future, we plan to further improve the application’s robustness by incorporating a larger and more comprehensive dataset. Additionally, we intend to conduct thorough evaluations to assess the usability and performance of the application.

REFERENCES

[1] X. Zhou and R. Zafarani, “A survey of fake news: Fundamental theories, detection methods, and opportunities,” ACM Computing Surveys (CSUR), vol. 53, no. 5, pp. 1–40, 2020.

[2] A. Sanaullah, A. Das, A. Das, M. A. Kabir, and K. Shu, “Applications of machine learning for covid-19 misinformation: a systematic review,” Social Network Analysis and Mining, vol. 12, no. 1, p. 94, 2022.

[3] D. M. Lazer, M. A. Baum, Y. Benkler, A. J. Berinsky, K. M. Greenhill, F. Menczer, M. J. Metzger, B. Nyhan, G. Pennycook, D. Rothschild, and et al., “The science of fake news,” Science, vol. 359, no. 6380, p. 1094–1096, 2018.

[4] A. Watson, “Problems with finding coronavirus news worldwide 2020,” https://www.statista.com/statistics/1104506/coronavirusnews-opinions-worldwide/, 2020, accessed: 30 August, 2023.

[5] ——, “Sharing of made-up news on social networks in the u.s. 2020,” https://www.statista.com/statistics/657111/fake-news-sharing-online/, 2023, accessed: 30 August, 2023.

[6] S. Vosoughi, D. Roy, and S. Aral, “The spread of true and false news online,” Science, vol. 359, no. 6380, p. 1146–1151, 2018.

[7] M. A. Britt, J.-F. Rouet, D. Blaum, and K. Millis, “A reasoned approach to dealing with fake news,” Policy Insights from the Behavioral and Brain Sciences, vol. 6, no. 1, p. 94–101, 2019.

[8] G. Pennycook and D. G. Rand, “The psychology of fake news,” Trends in Cognitive Sciences, vol. 25, no. 5, p. 388–402, 2021.

[9] T. L. I. Diseases, “The covid-19 infodemic,” The Lancet Infectious Diseases, vol. 20, no. 8, p. 875, 2020.

[10] W. Samek, T. Wiegand, and K.-R. Muller, “Explainable artificial in- ¨ telligence: Understanding, visualizing and interpreting deep learning models,” CoRR, vol. abs/1708.08296, 2017.

[11] J. Ayoub, X. J. Yang, and F. Zhou, “Combat COVID-19 infodemic using explainable natural language processing models,” Information Processing & Management, p. 102569, mar 2021.

[12] N. L. Kolluri and D. Murthy, “CoVerifi: A COVID-19 news verification system,” Online Social Networks and Media, vol. 22, 2021.

[13] K. Shu, S. Wang, L. Cui, D. Lee, and H. Liu, “dEFEND: Explainable Fake News Detection,” dl.acm.org, pp. 395–405, jul 2019.

[14] Y. Ma, D. Towey, T. Yueh Chen, and Z. Quan Zhou, “Metamorphic testing of fake news detection software,” 2021 IEEE 45th Annual Computers, Software, and Applications Conference (COMPSAC), 2021.

[15] A. B. Shams, E. Hoque Apu, A. Rahman, M. M. Sarker Raihan, N. Siddika, R. B. Preo, M. R. Hussein, S. Mostari, and R. Kabir, “Web search engine misinformation notifier extension (seminext): A machine learning based approach during covid-19 pandemic,” Healthcare, vol. 9, no. 2, p. 156, 2021.

[16] F. Yang, S. K. Pentyala, S. Mohseni, M. Du, H. Yuan, R. Linder, E. D. Ragan, S. Ji, and X. B. Hu, “Xfake: Explainable fake news detector with visualizations,” The World Wide Web Conference on - WWW ’19, 2019.

[17] Poynter Institute, “Politifact,” https://www.politifact.com/, accessed: 30 August, 2023.

[18] R. Sawant, “Bunyip,” https://awesomeopensource.com/project/CT83/ Bunyip, accessed: 30 August, 2023.

[19] L. Cui and D. Lee, “CoAID: COVID-19 healthcare misinformation dataset,” 2020.

[20] M. Cheng, S. Wang, X. Yan, T. Yang, W. Wang, Z. Huang, X. Xiao, S. Nazarian, and P. Bogdan, “A COVID-19 rumor dataset,” Frontiers in Psychology, vol. 12, 2021.

[21] Z. Li, F. Liu, W. Yang, S. Peng, and J. Zhou, “A survey of convolutional neural networks: Analysis, applications, and prospects,” IEEE Trans. Neural Netw., vol. 33, no. 12, pp. 6999–7019, 2022.

[22] J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “BERT: Pretraining of deep bidirectional transformers for language understanding,” in Proceedings of NAACL-HLT. Minneapolis, Minnesota: Association for Computational Linguistics, 2019, p. 4171–4186.

[23] C. Colon-Ruiz and I. Segura-Bedmar, “Comparing deep learning archi- ´ tectures for sentiment analysis on drug reviews,” Journal of Biomedical Informatics, vol. 110, 2020.

[24] J. Y. Khan, M. T. Khondaker, S. Afroz, G. Uddin, and A. Iqbal, “A benchmark study of machine learning models for online fake news detection,” Machine Learning with Applications, vol. 4, 2021.

[25] A. Ezen-Can, “A comparison of LSTM and BERT for small corpus,” ArXiv, vol. abs/2009.05451, 2020.

[26] S. M. Lundberg and S.-I. Lee, “A unified approach to interpreting model predictions,” in Proceedings of the 31st International Conference on Neural Information Processing Systems, 2017, p. 4768–4777.

[27] M. T. Ribeiro, S. Singh, and C. Guestrin, ““why should i trust you?”: Explaining the predictions of any classifier,” in Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016, p. 1135–1144.