Testing the Generalization of Neural Language Models for COVID-19 Misinformation Detection
arXiv:2111.07819 · doi:10.1007/978-3-030-96957-8_33
Abstract
A drastic rise in potentially life-threatening misinformation has been a by-product of the COVID-19 pandemic. Computational support to identify false information within the massive body of data on the topic is crucial to prevent harm. Researchers proposed many methods for flagging online misinformation related to COVID-19. However, these methods predominantly target specific content types (e.g., news) or platforms (e.g., Twitter). The methods' capabilities to generalize were largely unclear so far. We evaluate fifteen Transformer-based models on five COVID-19 misinformation datasets that include social media posts, news articles, and scientific papers to fill this gap. We show tokenizers and models tailored to COVID-19 data do not provide a significant advantage over general-purpose ones. Our study provides a realistic assessment of models for detecting COVID-19 misinformation. We expect that evaluating a broad spectrum of datasets and models will benefit future research in developing misinformation detection systems.
References in corpus (13)
- BioBERT: a pre-trained biomedical language representation model for biomedical text mining
- The COVID-19 Social Media Infodemic
- SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systems
- Publicly Available Clinical BERT Embeddings
- CORD-19: The COVID-19 Open Research Dataset
- DeBERTa: Decoding-enhanced BERT with Disentangled Attention
- ReCOVery: A Multimodal Repository for COVID-19 News Credibility Research
- CoAID: COVID-19 Healthcare Misinformation Dataset
- Multi-sense embeddings through a word sense disambiguation process
- Identifying Machine-Paraphrased Plagiarism
- Characterizing COVID-19 Misinformation Communities Using a Novel Twitter Dataset
- Are Neural Language Models Good Plagiarists? A Benchmark for Neural Paraphrase Detection
- Enhanced word embeddings using multi-semantic representation through lexical chains