Toward Automated Fact-Checking: Detecting Check-worthy Factual Claims by ClaimBuster

By Naeemul Hassan, Fatma Arslan, Chengkai Li, Mark Tremayne. Knowledge Discovery and Data Mining, 2017

379 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Sociology and Political Science

View Paper: https://www.semanticscholar.org/paper/6e99d06b4f2a53f8f6d1f5a51c4fbbee45322ab0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Sociology and Political Science

Citations in the corpus

Citation Needed: A Taxonomy and Algorithmic Assessment of Wikipedia's Verifiability (2019, background): “wever,these approaches cannot be applied in our case because they make the assumption that any provided statement is of factual nature. Research on the automated fact detectors in political discourse [23, 32, 39] is the work in this domain that is most closely related to ours.Whiletheseeffortshavede”
Understanding the Promise and Limits of Automated Fact-Checking (2018, background): “For instance, ClaimBuster, an AFC platform developed at the University of Texas-Arlington, at a cost of roughly $150,000 so far, trained on about 20,000 sentences from past US presidential debates, classified by paid human coders, to learn to distinguish ‘check-worthy’ factual claims from opinions a”
A Survey of Fake News (2020, background): “…in many ways, such as by verifying if the title of the news article is a clickbait [Zhou et al. 2019a], if its content will trigger widespread discussions on social media [Vosoughi et al. 2018], or if its topic relates to national affairs and matches with public concerns [Hassan et al. 2017a].”
Preserving integrity in online social networks (2020, background): “While some studies begin by extacting claims that are worth checking from the post [43, 44, 51, 58], most work assumes that claims are given as input and focus on determining the truthfulness of those claims.”
Explainable Automated Fact-Checking for Public Health Claims (2020, background): “A number of recent works in automated fact-checking look at various formulations of fact-checking and its analogous tasks (Ferreira and Vla-chos, 2016; Hassan et al., 2017; Zlatkova et al., 2019).”
Automated Fact-Checking for Assisting Human Fact-Checkers (2021, methodology): “After retrieving tweets in response to an input search query, the system scores tweets by check-worthiness using the ClaimBuster model and also attempts to verify each tweet by retrieving similar claims previously fact-checked by fact-checking organizations (e.g., PolitiFact).”
Explainable Fact Checking with Probabilistic Answer Set Programming (2019, background): “There are two main tasks in computational fact checking: (1) monitor and spot claims [9, 11], (2) check claims and explain outcomes.”
Automated Fact Checking: Task Formulations, Methods and Future Directions (2018, methodology): “Text classiﬁcation on claims alone has been used for the related task of detecting fact-check worthy claims (Hassan et al., 2017a).”