COVID-19 on Social Media: Analyzing Misinformation in Twitter Conversations

The ongoing Coronavirus (COVID-19) pandemic highlights theinter-connectedness of our present-day globalized world. With social distancingpolicies in place, virtual communication has become an important source of(mis)information. As increasing number of people rely on social media platformsfor news, identifying misinformation and uncovering the nature of onlinediscourse around COVID-19 has emerged as a critical task. To this end, wecollected streaming data related to COVID-19 using the Twitter API, startingMarch 1, 2020. We identified unreliable and misleading contents based onfact-checking sources, and examined the narratives promoted in misinformationtweets, along with the distribution of engagements with these tweets. Inaddition, we provide examples of the spreading patterns of prominentmisinformation tweets. The analysis is presented and updated on a publicallyaccessible dashboard (https://usc-melady.github.io/COVID-19-Tweet-Analysis) totrack the nature of online discourse and misinformation about COVID-19 onTwitter from March 1 - June 5, 2020. The dashboard provides a daily list ofidentified misinformation tweets, along with topics, sentiments, and emergingtrends in the COVID-19 Twitter discourse. The dashboard is provided to improvevisibility into the nature and quality of information shared online, andprovide real-time access to insights and information extracted from thedataset.