Fact-Checking In Complex Networks : A hybrid textual-social based approach

As false information and fake news continue propagating throughout the internet and social networks, the need for fact-checking operations arises, with notable examples politics (such as the 2016 USA Elections) and public health (COVID19). A number of solutions have been proposed to deal with this problem and limit the spread of false information, both manual and automatic. Undoubtedly the manual approaches done on websites such as PolitiFact.com, FactCheck.org and Snopes.com aren’t a viable long term solution: put simply, disinformation is increasing and human fact-checkers simply don’t scale up at the same rate. This paper presents our contributions, which include: (i) An automated solution for fact-checking using state-of-the-art Language Models (LMs) and five well known datasets containing annotated claims/tweets to fine-tune each LM and classify a given claim through textual context; and (ii) A custom architecture, the Hybrid Fake News Classifier, that utilizes both textual context and social context by combining both LLMs and Graph AutoEncoders (GAEs). We show that fine-tuning a LM with the correct settings can achieve an high accuracy and F1-scores, better than the majority of fact-checking methods that exist today. Moreover, the Hybrid Fake News Classifier achieves better than SOTA accuracy and F1-score, which shows that we can use the social interactions of users in a network as an additional key attribute next-to textual claims for fake-news detection.