Human-in-the-loop Evaluation for Early Misinformation Detection: A Case Study of COVID-19 Treatments
This work addresses the challenge of identifying and verifying emerging misinformation in social media for public health domains, though it is incremental as it builds on existing NLP techniques.
The researchers tackled the problem of early misinformation detection by developing a human-in-the-loop evaluation framework for fact-checking novel claims, specifically applied to COVID-19 treatments, and demonstrated its feasibility with a baseline system using NLP methods.
We present a human-in-the-loop evaluation framework for fact-checking novel misinformation claims and identifying social media messages that support them. Our approach extracts check-worthy claims, which are aggregated and ranked for review. Stance classifiers are then used to identify tweets supporting novel misinformation claims, which are further reviewed to determine whether they violate relevant policies. To demonstrate the feasibility of our approach, we develop a baseline system based on modern NLP methods for human-in-the-loop fact-checking in the domain of COVID-19 treatments. We make our data and detailed annotation guidelines available to support the evaluation of human-in-the-loop systems that identify novel misinformation directly from raw user-generated content.