Exploring Thematic Coherence in Fake News
Martins Samuel Dogo, Deepak P, Anna Jurek-Loughrey

TL;DR
This paper investigates the use of topic models to analyze thematic coherence in fake news, revealing that fake news exhibits greater deviation in coherence compared to real news across multiple datasets.
Contribution
It introduces a novel approach using topic models to quantify thematic coherence differences between fake and real news across various domains.
Findings
Fake news shows higher thematic deviation in coherence.
Topic models effectively differentiate fake from real news.
Results validated on seven diverse datasets.
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.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMisinformation and Its Impacts · Topic Modeling · Sentiment Analysis and Opinion Mining
