Detecting COVID-19 Misinformation on Social Media

Tamanna Hossain, Robert L. Logan IV, Arjuna Ugarte, Yoshitomo Matsubara, Sameer Singh, Sean Young

Keywords: COVID-19, misinformation, dataset, NLP, NLI, semantic similarity

TL;DR: Dataset for detecting COVID-19 misinformation on social media and evaluation of existing NLP models.

Abstract: The ongoing pandemic has heightened the need for developing tools to flag COVID-19-related misinformation on the internet, specifically on social media such as Twitter. However, due to novel language and the rapid change of information, existing misinformation detection datasets will not be effective for evaluating systems designed to detect misinformation on this topic. To facilitate research on this task, we release a dataset of 4.8K expert-annotated social media posts to evaluate the performance of misinformation detection systems on 86 different pieces of misinformation relating to COVID-19. We evaluate existing NLP systems on this dataset, identifying key challenges for future models to improve upon.