Skip to main content
Article
Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document
Findings of the Association for Computational Linguistics: EMNLP 2022
  • Shaden Shaar, Cornell University
  • Nikola Georgiev, Sofia University St. Kliment Ohridski
  • Firoj Alam, Qatar Computing Research Institute
  • Giovanni Da San Martino, Università degli Studi di Padova
  • Aisha Mohamed, University of Wisconsin-Madison
  • Preslav Nakov, Mohamed Bin Zayed University of Artificial Intelligence
Document Type
Conference Proceeding
Abstract

Given the recent proliferation of false claims online, there has been a lot of manual fact-checking effort. As this is very time-consuming, human fact-checkers can benefit from tools that can support them and make them more efficient. Here, we focus on building a system that could provide such support. Given an input document, it aims to detect all sentences that contain a claim that can be verified by some previously fact-checked claims (from a given database). The output is a re-ranked list of the document sentences, so that those that can be verified are ranked as high as possible, together with corresponding evidence. Unlike previous work, which has looked into claim retrieval, here we take a document-level perspective. We create a new manually annotated dataset for this task, and we propose suitable evaluation measures. We further experiment with a learning-to-rank approach, achieving sizable performance gains over several strong baselines. Our analysis demonstrates the importance of modeling text similarity and stance, while also taking into account the veracity of the retrieved previously fact-checked claims. We believe that this research would be of interest to fact-checkers, journalists, media, and regulatory authorities.

DOI
10.18653/v1/2022.findings-emnlp.151
Publication Date
12-1-2022
Comments

Archived with thanks to ACL Anthology

Preprint License: CC by 4.0 DEED

Uploaded 27 November 2023

Citation Information
S. Shaar, et al, "Assisting the Human Fact-Checkers: Detecting All Previously Fact-Checked Claims in a Document", in Findings of the Association for Computational Linguistics: EMNLP 2022, ACL, pp. 2069–2080, Dec 2022. doi:10.18653/v1/2022.findings-emnlp.151