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 language | English |
---|---|
Title of host publication | 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: proceedings |
Publisher | Springer, Cham |
Pages | 571-580 |
ISBN (Electronic) | 9783030659653 |
ISBN (Print) | 9783030659646 |
DOIs | |
Publication status | Published - 02 Feb 2021 |
Event | 8th International Workshop on News Recommendation and Analytics (INRA 2020) - Duration: 14 Sep 2020 → 14 Sep 2020 https://www.ntnu.no/wiki/pages/viewpage.action?pageId=188580623 |
Publication series
Name | Communications in Computer and Information Science |
---|---|
Publisher | Springer |
Volume | 1323 |
ISSN (Print) | 1865-0929 |
ISSN (Electronic) | 1865-0937 |
Workshop
Workshop | 8th International Workshop on News Recommendation and Analytics (INRA 2020) |
---|---|
Period | 14/09/2020 → 14/09/2020 |
Internet address |