Fake News Detection Algorithms Comparison and Application of XGBoost, SVM, and NB

Huaimin Wang ； Yuyao Ma ； Ye Deng ； Yihan Wang

《World Scientific Research Journal》 7卷1期 (2021/01) Pp. 323-329

https://doi.org/10.6911/WSRJ.202101_7(1).0041

摘要

Fake news affects areas such as politics, finance and technology. It is important to find a good method of detecting fake news in the presence of major events, such as the 2020 U.S. election. The purpose of this paper is to find the most suitable combination of common machine learning models and feature extraction algorithms for fake news detection. Three machine learning models, including Naïve Bayes (NB), Support Vector Machine (SVM) and XGBoost, along with different feature extraction algorithms are applied in the experiment. Result shows that XGBoost, with an accuracy of 98.6%, outperforms both SVM and NB. The result also shows that TF-IDF is the most suitable feature extraction algorithm for XGBoost. Future work on applying sentiment analysis to fake news detection and exploring cross-language fake news detection is expected. All these work will help solve the problem of fake news detection.

關鍵字

Fake news detection ； Naïve Bayes ； SVM ； XGBoost

參考文獻

Shu, K., Sliva, A., Wang, S., Tang, J., & Liu, H. (2017). Fake News Detection on Social Media: A Data Mining Perspective. ACM SIGKDD Explorations Newsletter, 19(1), 22–36.

Ladd, J. M. (2012). Why Americans Hate the News Media and How It Matters. Princeton University Press.

Turcotte, J., York, C., Irving, J., Scholl, R. M., & Pingree, R. J. (2015). News Recommendations from Social Media Opinion Leaders: Effects on Media Trust and Information Seeking. Journal of Computer-Mediated Communication, 20(5), 520–535.

Allcott, H., & Gentzkow, M. (2017). Social Media and Fake News in the 2016 Election. Journal of Economic Perspectives, 31(2), 211–236.

Bovet, A., & Makse, H. A. (2019). Influence of fake news in Twitter during the 2016 US presidential election. Nature Communications, 10(1), 7.