header

Time-Aware Evidence Ranking for Fact-Checking

20 Pages Posted: 19 Oct 2021 Publication Status: Accepted

See all articles by Liesbeth Allein

Liesbeth Allein

European Union - European Commission Joint Research Center

Isabelle Augenstein

University of Copenhagen

Marie-Francine Moens

KU Leuven

Abstract

Truth can vary over time. Fact-checking decisions on claim veracity should therefore take into account temporal information of both the claim and supporting or refuting evidence. In this work, we investigate the hypothesis that the timestamp of a Web page is crucial to how it should be ranked for a given claim. We delineate four temporal ranking methods that constrain evidence ranking differently and simulate hypothesis-specific evidence rankings given the evidence timestamps as gold standard. Evidence ranking in three fact-checking models is ultimately optimized using a learning-to-rank loss function. Our study reveals that time-aware evidence ranking not only surpasses relevance assumptions based purely on semantic similarity or position in a search results list, but also improves veracity predictions of time-sensitive claims in particular.

Suggested Citation

Allein, Liesbeth and Augenstein, Isabelle and Moens, Marie-Francine, Time-Aware Evidence Ranking for Fact-Checking. Journal of Web Semantics First Look , Available at SSRN: https://ssrn.com/abstract=3945441 or http://dx.doi.org/10.2139/ssrn.3945441

Liesbeth Allein (Contact Author)

European Union - European Commission Joint Research Center ( email )

Edificio Expo C
Inca Garcilaso, s/n
Sevilla, Sevilla E-41092
Spain

Isabelle Augenstein

University of Copenhagen ( email )

Nørregade 10
Copenhagen, København DK-1165
Denmark

Marie-Francine Moens

KU Leuven ( email )

Oude Markt 13
Leuven, Vlaams-Brabant 3000
Belgium

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Abstract Views
45
Downloads
7
PlumX Metrics