Creating task-generic features for fake news detection

Olivieri, Alex C. (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Shabani, Shaban (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Sokhn, Maria (University of Applied Sciences and Arts Western Switzerland (HES-SO Valais-Wallis)) ; Cudré-Mauroux, Philippe (University of Fribourg, Switzerland)

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.


Conference Type:
full paper
Faculty:
Economie et Services
School:
HEG-VS
Institute:
Institut Informatique de gestion
Subject(s):
Informatique
Publisher:
Grand Wailea, Maui, 8-11 January 2019
Date:
2019-01
Grand Wailea, Maui
8-11 January 2019
Pagination:
10 p.
Published in:
Proceedings of the 52nd Hawaii International Conference on System Sciences (HICSS) 2019
External resources:
Appears in Collection:



 Record created 2019-04-26, last modified 2019-10-22

Published version:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)