Leveraging Wikipedia article evolution for promotional tone detection

Christine De Kock, Andreas Vlachos


Abstract
Detecting biased language is useful for a variety of applications, such as identifying hyperpartisan news sources or flagging one-sided rhetoric. In this work we introduce WikiEvolve, a dataset for document-level promotional tone detection. Unlike previously proposed datasets, WikiEvolve contains seven versions of the same article from Wikipedia, from different points in its revision history; one with promotional tone, and six without it. This allows for obtaining more precise training signal for learning models from promotional tone detection. We adapt the previously proposed gradient reversal layer framework to encode two article versions simultaneously and thus leverage this additional training signal. In our experiments, our proposed adaptation of gradient reversal improves the accuracy of four different architectures on both in-domain and out-of-domain evaluation.
Anthology ID:
2022.acl-long.384
Volume:
Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5601–5613
Language:
URL:
https://aclanthology.org/2022.acl-long.384
DOI:
10.18653/v1/2022.acl-long.384
Bibkey:
Cite (ACL):
Christine De Kock and Andreas Vlachos. 2022. Leveraging Wikipedia article evolution for promotional tone detection. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 5601–5613, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Leveraging Wikipedia article evolution for promotional tone detection (De Kock & Vlachos, ACL 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.acl-long.384.pdf
Video:
 https://aclanthology.org/2022.acl-long.384.mp4
Code
 christinedekock11/wiki-evolve