Explainable Automated Fact-Checking for Public Health Claims
This addresses the lack of fact-checking research for specialized domains like public health, though it is incremental as it extends existing methods to a new dataset.
The study tackled the problem of automated fact-checking for public health claims, which require specific expertise, by constructing a new dataset of 11.8K claims and showing that training on in-domain data improves performance in veracity prediction and explanation generation.
Fact-checking is the task of verifying the veracity of claims by assessing their assertions against credible evidence. The vast majority of fact-checking studies focus exclusively on political claims. Very little research explores fact-checking for other topics, specifically subject matters for which expertise is required. We present the first study of explainable fact-checking for claims which require specific expertise. For our case study we choose the setting of public health. To support this case study we construct a new dataset PUBHEALTH of 11.8K claims accompanied by journalist crafted, gold standard explanations (i.e., judgments) to support the fact-check labels for claims. We explore two tasks: veracity prediction and explanation generation. We also define and evaluate, with humans and computationally, three coherence properties of explanation quality. Our results indicate that, by training on in-domain data, gains can be made in explainable, automated fact-checking for claims which require specific expertise.