Lies Kill, Facts Save: Detecting COVID-19 Misinformation in Twitter

Online social networks (ONSs) such as Twitter have grown to be very useful tools for the dissemination of information. However, they have also become a fertile ground for the spread of false information, particularly regarding the ongoing coronavirus disease 2019 (COVID-19) pandemic. Best described as an infodemic, there is a great need, now more than ever, for scientific fact-checking and misinformation detection regarding the dangers posed by these tools with regards to COVID-19. In this article, we analyze the credibility of information shared on Twitter pertaining the COVID-19 pandemic. For our analysis, we propose an ensemble-learning-based framework for verifying the credibility of a vast number of tweets. In particular, we carry out analyses of a large dataset of tweets conveying information regarding COVID-19. In our approach, we classify the information into two categories: credible or non-credible. Our classifications of tweet credibility are based on various features, including tweet- and user-level features. We conduct multiple experiments on the collected and labeled dataset. The results obtained with the proposed framework reveal high accuracy in detecting credible and non-credible tweets containing COVID-19 information.