Classification aware neural topic model for COVID-19 disinformation categorisation

Abstract

The explosion of disinformation accompanying the COVID-19 pandemic has overloaded fact-checkers and media worldwide, and brought a new major challenge to government responses worldwide. Not only is disinformation creating confusion about medical science amongst citizens, but it is also amplifying distrust in policy makers and governments. To help tackle this, we developed computational methods to categorise COVID-19 disinformation. The COVID-19 disinformation categories could be used for a) focusing fact-checking efforts on the most damaging kinds of COVID-19 disinformation; b) guiding policy makers who are trying to deliver effective public health messages and counter effectively COVID-19 disinformation. This paper presents: 1) a corpus containing what is currently the largest available set of manually annotated COVID-19 disinformation categories; 2) a classification-aware neural topic model (CANTM) designed for COVID-19 disinformation category classification and topic discovery; 3) an extensive analysis of COVID-19 disinformation categories with respect to time, volume, false type, media type and origin source.

Factors affecting individual online rumor sharing behavior in the COVID-19 pandemic

“… Cinelli et al (2020) collected rumor data on five social media platforms and analyzed the rumor amplification among the different platforms. Song et al (2020) provided a large COVID-19 rumor dataset and adopted a neural topic model to label the topic classification. Other studies include the research on disinformation propagation ( Huang & Carley, 2020 ; Li et al, 2020 ); examining the social, cultural, and political entanglements ( Leng et al, 2020 ); and identifying disinformation campaigns ( Vargas et al, 2020 ).…”

Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society

“…The closest work to ours is that of Song et al (2020), who collected false and misleading claims about COVID-19 from IFCN Poynter, and annotated them as (1) Public authority, (2) Community spread and impact, (3) Medical advice, selftreatments, and virus effects, (4) Prominent actors, (5) Conspiracies, (6) Virus transmission, (7) Virus origins and properties, (8) Public reaction, and (9) Vaccines, medical treatments, and tests. These categories partially overlap with ours, but account for less perspectives.…”

“…There are a number of COVID-19 Twitter datasets: some unlabeled (Chen et al, 2020;Banda et al, 2021;Haouari et al, 2021), some automatically labeled with location information Qazi et al, 2020), some labeled using distant supervision (Cinelli et al, 2020;Zhou et al, 2020), and some manually annotated (Song et al, 2020;Vidgen et al, 2020;Shahi and Nandini, 2020;Pulido et al, 2020;Dharawat et al, 2020).…”

Findings of the NLP4IF-2021 Shared Tasks on Fighting the COVID-19 Infodemic and Censorship Detection

“…Vidgen et al (2020) studied COVID-19 prejudices using a manually labeled dataset of 20K tweets with the following labels: hostile, criticism, prejudice, and neutral. Song et al (2021) collected a dataset of false and misleading claims about COVID-19 from IFCN Poynter, which they manually annotated with the following ten disinformation-related categories:…”