Abstract
Election manifestos document the intentions, motives, and views of political parties. They are often used for analysing a party’s fine-grained position on a particular issue, as well as for coarse-grained positioning of a party on the left–right spectrum. In this paper we propose a two-stage model for automatically performing both levels of analysis over manifestos. In the first step we employ a hierarchical multi-task structured deep model to predict fine- and coarse-grained positions, and in the second step we perform post-hoc calibration of coarse-grained positions using probabilistic soft logic. We empirically show that the proposed model outperforms state-of-art approaches at both granularities using manifestos from twelve countries, written in ten different languages.- Anthology ID:
- N18-1178
- Volume:
- Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers)
- Month:
- June
- Year:
- 2018
- Address:
- New Orleans, Louisiana
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1964–1974
- Language:
- URL:
- https://aclanthology.org/N18-1178
- DOI:
- 10.18653/v1/N18-1178
- Cite (ACL):
- Shivashankar Subramanian, Trevor Cohn, and Timothy Baldwin. 2018. Hierarchical Structured Model for Fine-to-Coarse Manifesto Text Analysis. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers), pages 1964–1974, New Orleans, Louisiana. Association for Computational Linguistics.
- Cite (Informal):
- Hierarchical Structured Model for Fine-to-Coarse Manifesto Text Analysis (Subramanian et al., NAACL 2018)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/N18-1178.pdf