Exploring Thematic Coherence in Fake News

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The spread of fake news remains a serious global issue; understanding
and curtailing it is paramount. One way of differentiating between deceptive and
truthful stories is by analyzing their coherence. This study explores the use of
topic models to analyze the coherence of cross-domain news shared online.
Experimental results on seven cross-domain datasets demonstrate that fake news
shows a greater thematic deviation between its opening sentences and its
remainder.
Original languageEnglish
Title of host publication8th International Workshop on News Recommendation and Analytics (INRA 2020)
Publication statusAccepted - 25 Jul 2020
Event8th International Workshop on News Recommendation and Analytics (INRA 2020) -
Duration: 14 Sep 202014 Sep 2020
https://www.ntnu.no/wiki/pages/viewpage.action?pageId=188580623

Publication series

NameCEUR Workshop Proceedings
ISSN (Electronic)1613-0073

Workshop

Workshop8th International Workshop on News Recommendation and Analytics (INRA 2020)
Period14/09/202014/09/2020
Internet address

Fingerprint

Dive into the research topics of 'Exploring Thematic Coherence in Fake News'. Together they form a unique fingerprint.

Cite this