Standing on the Shoulders of Guardians: Novel Methodologies to Combat Fake News

Abstract

Fake news can signifiFake news and misinformation are one of the most pressing issues of modern society. In fighting against fake news, many fact-checking systems such as human-based fact-checking sites (e.g., snopes.com and politifact.com) and automatic detection systems have been developed in recent years. However, online users still keep sharing fake news even when it has been debunked. It means that early fake news detection may be insufficient and we need complementary approaches to mitigate the spread of misinformation. In this chapter, we introduce novel methods to intervene the spread of fake news and misinformation. In particular, we (1) leverage online users named guardians, who cite fact-checking sites as credible evidences to fact-check information in public discourse, (2) propose two novel frameworks – the first one is a recommender system to personalize factchecking articles1 and the second one is a text generation framework2 to generate responses with fact-checking intention. Both frameworks are designed to increase the guardians’ engagement in fact-checking activities. Experimental results showed that our recommender system improves competitive baselines significantly by 10~20%, and the text generation framework is able to generate relevant responses and outperforms state-of-the-art models by achieving up to 30% improvement. Our qualitative study also confirms that the superiority of our generated responses compared with responses generated from the existing models.cantly misinform people who often rely on online sources and social media for their information. Current research on fake news detection has mostly focused on analyzing fake news content and how it propagates on a network of users. In this paper, we emphasize the detection of fake news by assessing its credibility. By analyzing public fake news data, we show that information on news sources (and authors) can be a strong indicator of credibility. Our findings suggest that an author’s history of association with fake news, and the number of authors of a news article, can play a significant role in detecting fake news. Our approach can help improve traditional fake news detection methods, wherein content features are often used to detect fake news.