Automated Fact Checking: Task formulations, methods and future directions

TL;DR

This paper surveys automated fact checking research, unifies diverse task formulations and methods, emphasizes the role of evidence, and suggests future directions for NLP in combating misinformation.

Contribution

It provides a comprehensive overview of fact checking research, standardizes terminology, and highlights evidence as a key component across different approaches.

Findings

Identification of diverse fact checking methodologies

Highlighting evidence as a crucial factor in verification

Proposing future research directions in NLP for fact checking

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.