Automated Fact Checking: Task formulations, methods and future directions

Abstract

The recently increased focus on misinformation has stimulated research in fact checking, the task of assessing the truthfulness of a claim. Research in automating this task has been conducted in a variety of disciplines including natural language processing, machine learning, knowledge representation, databases, and journalism. While there has been substantial progress, relevant papers and articles have been published in research communities that are often unaware of each other and use inconsistent terminology, thus impeding understanding and further progress. In this paper we survey automated fact checking research stemming from natural language processing and related disciplines, unifying the task formulations and methodologies across papers and authors. Furthermore, we highlight the use of evidence as an important distinguishing factor among them cutting across task formulations and methods. We conclude with proposing avenues for future NLP research on automated fact checking.

Published at the 27th International Conference on Computational Linguistics (COLING 2018)

References in corpus (2)

• Evidence Aggregation for Answer Re-Ranking in Open-Domain Question Answering
• Program Induction by Rationale Generation : Learning to Solve and Explain Algebraic Word Problems

Cited by in corpus (10)

• Studying Fake News Spreading, Polarisation Dynamics, and Manipulation by Bots: a Tale of Networks and Language
• Crowdsourced Fact-Checking at Twitter: How Does the Crowd Compare With Experts?
• Dataset of Fake News Detection and Fact Verification: A Survey
• Information Credibility in the Social Web: Contexts, Approaches, and Open Issues
• CsFEVER and CTKFacts: Acquiring Czech data for fact verification
• Assessing the Potential of Generative Agents in Crowdsourced Fact-Checking
• The False COVID-19 Narratives That Keep Being Debunked: A Spatiotemporal Analysis
• Unsupervised Question Answering for Fact-Checking
• Fact Checking via Path Embedding and Aggregation
• Checking Fact Worthiness using Sentence Embeddings