Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy

Jiwoo Hong, Yejin Cho, Jiyoung Han, Jaemin Jung, James Thorne

Abstract
We address an important gap in detecting political bias in news articles. Previous works that perform document classification can be influenced by the writing style of each news outlet, leading to overfitting and limited generalizability. Our approach overcomes this limitation by considering both the sentence-level semantics and the document-level rhetorical structure, resulting in a more robust and style-agnostic approach to detecting political bias in news articles. We introduce a novel multi-head hierarchical attention model that effectively encodes the structure of long documents through a diverse ensemble of attention heads. While journalism follows a formalized rhetorical structure, the writing style may vary by news outlet. We demonstrate that our method overcomes this domain dependency and outperforms previous approaches for robustness and accuracy. Further analysis and human evaluation demonstrate the ability of our model to capture common discourse structures in journalism.
Anthology ID:
2023.findings-emnlp.377
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2023
Month:
December
Year:
2023
Address:
Singapore
Editors:
Houda Bouamor, Juan Pino, Kalika Bali
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5664–5686
Language:
URL:
https://aclanthology.org/2023.findings-emnlp.377
DOI:
10.18653/v1/2023.findings-emnlp.377
Bibkey:
Cite (ACL):
Jiwoo Hong, Yejin Cho, Jiyoung Han, Jaemin Jung, and James Thorne. 2023. Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy. In Findings of the Association for Computational Linguistics: EMNLP 2023, pages 5664–5686, Singapore. Association for Computational Linguistics.
Cite (Informal):
Disentangling Structure and Style: Political Bias Detection in News by Inducing Document Hierarchy (Hong et al., Findings 2023)
Copy Citation:
PDF:
https://preview.aclanthology.org/ingest-2024-clasp/2023.findings-emnlp.377.pdf
PDF Search