Two Stage Transformer Model for COVID-19 Fake News Detection and Fact Checking
This research aims to help social media users and platforms identify and mitigate the spread of COVID-19 misinformation, which can lead to public health risks; it is an incremental improvement on existing methods.
This paper addresses the problem of COVID-19 fake news detection by proposing a two-stage transformer model. The model first retrieves relevant facts for user claims and then verifies the truthfulness of the claim by computing textual entailment between the claim and retrieved facts. The BERT and ALBERT model pipeline achieved the best results.
The rapid advancement of technology in online communication via social media platforms has led to a prolific rise in the spread of misinformation and fake news. Fake news is especially rampant in the current COVID-19 pandemic, leading to people believing in false and potentially harmful claims and stories. Detecting fake news quickly can alleviate the spread of panic, chaos and potential health hazards. We developed a two stage automated pipeline for COVID-19 fake news detection using state of the art machine learning models for natural language processing. The first model leverages a novel fact checking algorithm that retrieves the most relevant facts concerning user claims about particular COVID-19 claims. The second model verifies the level of truth in the claim by computing the textual entailment between the claim and the true facts retrieved from a manually curated COVID-19 dataset. The dataset is based on a publicly available knowledge source consisting of more than 5000 COVID-19 false claims and verified explanations, a subset of which was internally annotated and cross-validated to train and evaluate our models. We evaluate a series of models based on classical text-based features to more contextual Transformer based models and observe that a model pipeline based on BERT and ALBERT for the two stages respectively yields the best results.