Joint Estimation of User And Publisher Credibility for Fake News Detection

Fast propagation, ease-of-access, and low cost have made social media an increasingly popular means for news consumption. However, this has also led to an increase in the preponderance of fake news. Widespread propagation of fake news can be detrimental to society, and this has created enormous interest in fake news detection on social media. Many approaches to fake news detection use the news content, social context, or both. In this work, we look at fake news detection as a problem of estimating the credibility of both the news publishers and users that propagate news articles. We introduce a new approach called the credibility score-based model that can jointly infer fake news and credibility scores for publishers and users. We use a state-of-the-art statistical relational learning framework called probabilistic soft logic to perform this joint inference effectively. We show that our approach is accurate at both fake news detection and inferring credibility scores. Further, our model can easily integrate any auxiliary information that can aid in fake news detection. Using the FakeNewsNet dataset, we show that our approach significantly outperforms previous approaches at fake news detection by up to 10% in recall and 4% in accuracy. Furthermore, the credibility scores learned for both publishers and users are representative of their true behavior.