Classification Aware Neural Topic Model and its Application on a New COVID-19 Disinformation Corpus

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.

This is arXiv version of "Classification Aware Neural Topic Model for COVID-19 Disinformation Categorisation"

References in corpus (31)

• Adam: A Method for Stochastic Optimization
• Auto-Encoding Variational Bayes
• HuggingFace's Transformers: State-of-the-art Natural Language Processing
• Stochastic Backpropagation and Approximate Inference in Deep Generative Models
• XLNet: Generalized Autoregressive Pretraining for Language Understanding
• The COVID-19 Social Media Infodemic
• Semi-Supervised Learning with Deep Generative Models
• Supervised Topic Models
• Tracking Social Media Discourse About the COVID-19 Pandemic: Development of a Public Coronavirus Twitter Data Set
• A large-scale COVID-19 Twitter chatter dataset for open scientific research -- an international collaboration
• Framing COVID-19: How we conceptualize and discuss the pandemic on Twitter
• Topic Models Conditioned on Arbitrary Features with Dirichlet-multinomial Regression
• A first look at COVID-19 information and misinformation sharing on Twitter
• Discovering Discrete Latent Topics with Neural Variational Inference
• Neural Variational Inference for Text Processing
• Language-agnostic BERT Sentence Embedding
• ReCOVery: A Multimodal Repository for COVID-19 News Credibility Research
• Neural Variational Inference and Learning in Belief Networks
• Autoencoding Variational Inference For Topic Models
• COVID-19 on Social Media: Analyzing Misinformation in Twitter Conversations
• GeoCoV19: A Dataset of Hundreds of Millions of Multilingual COVID-19 Tweets with Location Information
• Two Stage Transformer Model for COVID-19 Fake News Detection and Fact Checking
• Neural Models for Documents with Metadata
• COVID-19 Twitter Dataset with Latent Topics, Sentiments and Emotions Attributes
• Large-scale, Language-agnostic Discourse Classification of Tweets During COVID-19
• Is Working From Home The New Norm? An Observational Study Based on a Large Geo-tagged COVID-19 Twitter Dataset
• Risk Communication in Asian Countries: COVID-19 Discourse on Twitter
• Mega-COV: A Billion-Scale Dataset of 100+ Languages for COVID-19
• QMUL-SDS at CheckThat! 2020: Determining COVID-19 Tweet Check-Worthiness Using an Enhanced CT-BERT with Numeric Expressions
• Cultural Convergence: Insights into the behavior of misinformation networks on Twitter
• Discriminative Topic Modeling with Logistic LDA

Cited by in corpus (10)

• A Survey on Neural Topic Models: Methods, Applications, and Challenges
• BERT-Deep CNN: State-of-the-Art for Sentiment Analysis of COVID-19 Tweets
• A hybrid transformer and attention based recurrent neural network for robust and interpretable sentiment analysis of tweets
• Characterizing COVID-19 Misinformation Communities Using a Novel Twitter Dataset
• Like Article, Like Audience: Enforcing Multimodal Correlations for Disinformation Detection
• A Survey of COVID-19 Misinformation: Datasets, Detection Techniques and Open Issues
• What distinguishes conspiracy from critical narratives? A computational analysis of oppositional discourse
• The False COVID-19 Narratives That Keep Being Debunked: A Spatiotemporal Analysis
• Multistage BiCross encoder for multilingual access to COVID-19 health information
• Fighting the COVID-19 Infodemic: Modeling the Perspective of Journalists, Fact-Checkers, Social Media Platforms, Policy Makers, and the Society