Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection

Nguyen Vo, Kyumin Lee


Abstract
The widespread of fake news and misinformation in various domains ranging from politics, economics to public health has posed an urgent need to automatically fact-check information. A recent trend in fake news detection is to utilize evidence from external sources. However, existing evidence-aware fake news detection methods focused on either only word-level attention or evidence-level attention, which may result in suboptimal performance. In this paper, we propose a Hierarchical Multi-head Attentive Network to fact-check textual claims. Our model jointly combines multi-head word-level attention and multi-head document-level attention, which aid explanation in both word-level and evidence-level. Experiments on two real-word datasets show that our model outperforms seven state-of-the-art baselines. Improvements over baselines are from 6% to 18%. Our source code and datasets are released at https://github.com/nguyenvo09/EACL2021.
Anthology ID:
2021.eacl-main.83
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
965–975
Language:
URL:
https://aclanthology.org/2021.eacl-main.83
DOI:
10.18653/v1/2021.eacl-main.83
Bibkey:
Cite (ACL):
Nguyen Vo and Kyumin Lee. 2021. Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 965–975, Online. Association for Computational Linguistics.
Cite (Informal):
Hierarchical Multi-head Attentive Network for Evidence-aware Fake News Detection (Vo & Lee, EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2021.eacl-main.83.pdf
Code
 nguyenvo09/EACL2021
Data
PolitiFactSnopes