Improving Neural Political Statement Classification with Class Hierarchical Information

Erenay Dayanik, Andre Blessing, Nico Blokker, Sebastian Haunss, Jonas Kuhn, Gabriella Lapesa, Sebastian Pado


Abstract
Many tasks in text-based computational social science (CSS) involve the classification of political statements into categories based on a domain-specific codebook. In order to be useful for CSS analysis, these categories must be fine-grained. The typically skewed distribution of fine-grained categories, however, results in a challenging classification problem on the NLP side. This paper proposes to make use of the hierarchical relations among categories typically present in such codebooks:e.g., markets and taxation are both subcategories of economy, while borders is a subcategory of security. We use these ontological relations as prior knowledge to establish additional constraints on the learned model, thusimproving performance overall and in particular for infrequent categories. We evaluate several lightweight variants of this intuition by extending state-of-the-art transformer-based textclassifiers on two datasets and multiple languages. We find the most consistent improvement for an approach based on regularization.
Anthology ID:
2022.findings-acl.186
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2367–2382
Language:
URL:
https://aclanthology.org/2022.findings-acl.186
DOI:
10.18653/v1/2022.findings-acl.186
Bibkey:
Cite (ACL):
Erenay Dayanik, Andre Blessing, Nico Blokker, Sebastian Haunss, Jonas Kuhn, Gabriella Lapesa, and Sebastian Pado. 2022. Improving Neural Political Statement Classification with Class Hierarchical Information. In Findings of the Association for Computational Linguistics: ACL 2022, pages 2367–2382, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Improving Neural Political Statement Classification with Class Hierarchical Information (Dayanik et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.186.pdf
Software:
 2022.findings-acl.186.software.zip