Exploring thematic coherence in fake news

Martins Samuel Dogo*, Deepak Padmanabhan, Anna Jurek-Loughrey

*Corresponding author for this work

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

5 Citations (Scopus)
24 Downloads (Pure)


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 publicationProccedings of the workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020
PublisherSpringer Cham
ISBN (Electronic)9783030659653
ISBN (Print)9783030659646
Publication statusPublished - 02 Feb 2021
Event8th International Workshop on News Recommendation and Analytics (INRA 2020) -
Duration: 14 Sept 202014 Sept 2020

Publication series

NameCommunications in Computer and Information Science
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937


Workshop8th International Workshop on News Recommendation and Analytics (INRA 2020)
Internet address


Dive into the research topics of 'Exploring thematic coherence in fake news'. Together they form a unique fingerprint.

Cite this