Please use this identifier to cite or link to this item: https://doi.org/10.1145/3517214
Title: FANG: Leveraging Social Context for Fake News Detection Using Graph Representation
Authors: Nguyen, VH
Sugiyama, K 
Nakov, P 
Kan, MY 
Issue Date: 19-Mar-2022
Publisher: Association for Computing Machinery (ACM)
Citation: Nguyen, VH, Sugiyama, K, Nakov, P, Kan, MY (2022-03-19). FANG: Leveraging Social Context for Fake News Detection Using Graph Representation. Communications of the ACM 65 (4) : 124-132. ScholarBank@NUS Repository. https://doi.org/10.1145/3517214
Abstract: We propose Factual News Graph (FANG), a novel graphical social context representation and learning framework for fake news detection. Unlike previous contextual models that have targeted performance, our focus is on representation learning. Compared to transductive models, FANG is scalable in training as it does not have to maintain the social entities involved in the propagation of other news and is efficient at inference time, without the need to reprocess the entire graph. Our experimental results show that FANG is better at capturing the social context into a high-fidelity representation, compared to recent graphical and nongraphical models. In particular, FANG yields significant improvements for the task of fake news detection and is robust in the case of limited training data. We further demonstrate that the representations learned by FANG generalize to related tasks, such as predicting the factuality of reporting of a news medium.
Source Title: Communications of the ACM
URI: https://scholarbank.nus.edu.sg/handle/10635/228931
ISSN: 00010782
15577317
DOI: 10.1145/3517214
Appears in Collections:Elements
Staff Publications

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
3517214.pdf1.63 MBAdobe PDF

OPEN

PublishedView/Download

SCOPUSTM   
Citations

2
checked on Sep 25, 2022

Page view(s)

40
checked on Sep 29, 2022

Download(s)

3
checked on Sep 29, 2022

Google ScholarTM

Check

Altmetric


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.