Sifting the Arguments in Fake News to Boost a Disinformation Analysis Tool - Archive ouverte HAL Access content directly
Conference Papers Year : 2020

Sifting the Arguments in Fake News to Boost a Disinformation Analysis Tool

Abstract

The problem of disinformation spread on the Web is receiving an increasing attention, given the potential danger fake news represents for our society. Several approaches have been proposed in the literature to fight fake news, depending on the media such fake news are concerned with, i.e., text, images, or videos. Considering textual fake news, many open problems arise to go beyond simple keywords extraction based approaches. In this paper, we present a concrete application scenario where a fake news detection system is empowered with an argument mining model, to highlight and aid the analysis of the arguments put forward to support or oppose a given target topic in articles containing fake information.
Fichier principal
Vignette du fichier
DDCRVargFN.pdf (455.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02990781 , version 1 (05-11-2020)

Identifiers

  • HAL Id : hal-02990781 , version 1

Cite

Jérôme Delobelle, Amaury Delamaire, Elena Cabrio, Ramón Ruti, Serena Villata. Sifting the Arguments in Fake News to Boost a Disinformation Analysis Tool. NL4AI 2020 - 4th Workshop on Natural Language for Artificial Intelligence, Nov 2020, Online, Italy. ⟨hal-02990781⟩
182 View
154 Download

Share

Gmail Facebook X LinkedIn More