Creating Task-Generic Features for Fake News Detection

dc.contributor.author Olivieri, Alex
dc.contributor.author Shabani, Shaban
dc.contributor.author Sokhn, Maria
dc.contributor.author Cudré-Mauroux, Philippe
dc.date.accessioned 2019-01-03T00:35:18Z
dc.date.available 2019-01-03T00:35:18Z
dc.date.issued 2019-01-08
dc.description.abstract Information spreads at a pace never seen before on online platforms, even when this information is fake. Fake news can have substantial impact, for instance when it concern politics and influences the results of legislations or elections. Finding a methodology to verify if some piece of news is true or false is hence essential. In this work, we propose a methodology to create task-generic features that are paired with textual features in order to detect fake news. Task-generic features are created by elaborating on metadata attached to answers from Google’s search engine, and by using crowdsourcing for missing values. We experimentally validate our method on a dataset for fake news detection based on the PolitiFact website. Our results show an improvement in F1-Score of 3% over the state of the art, which is significant for a 6-class task.
dc.format.extent 10 pages
dc.identifier.doi 10.24251/HICSS.2019.624
dc.identifier.isbn 978-0-9981331-2-6
dc.identifier.uri http://hdl.handle.net/10125/59956
dc.language.iso eng
dc.relation.ispartof Proceedings of the 52nd Hawaii International Conference on System Sciences
dc.rights Attribution-NonCommercial-NoDerivatives 4.0 International
dc.rights.uri https://creativecommons.org/licenses/by-nc-nd/4.0/
dc.subject Truth and Lies: Deception and Cognition on the Internet
dc.subject Internet and the Digital Economy
dc.subject Crowdsourcing
dc.subject Fake News
dc.subject Google Custom Search
dc.subject Machine Learning
dc.subject Politics
dc.title Creating Task-Generic Features for Fake News Detection
dc.type Conference Paper
dc.type.dcmi Text
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
0516.pdf
Size:
319.92 KB
Format:
Adobe Portable Document Format
Description: