Text-Based Ideal Points

Keyon Vafa, Suresh Naidu, David Blei


Abstract
Ideal point models analyze lawmakers’ votes to quantify their political positions, or ideal points. But votes are not the only way to express a political position. Lawmakers also give speeches, release press statements, and post tweets. In this paper, we introduce the text-based ideal point model (TBIP), an unsupervised probabilistic topic model that analyzes texts to quantify the political positions of its authors. We demonstrate the TBIP with two types of politicized text data: U.S. Senate speeches and senator tweets. Though the model does not analyze their votes or political affiliations, the TBIP separates lawmakers by party, learns interpretable politicized topics, and infers ideal points close to the classical vote-based ideal points. One benefit of analyzing texts, as opposed to votes, is that the TBIP can estimate ideal points of anyone who authors political texts, including non-voting actors. To this end, we use it to study tweets from the 2020 Democratic presidential candidates. Using only the texts of their tweets, it identifies them along an interpretable progressive-to-moderate spectrum.
Anthology ID:
2020.acl-main.475
Volume:
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
Month:
July
Year:
2020
Address:
Online
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
5345–5357
Language:
URL:
https://aclanthology.org/2020.acl-main.475
DOI:
10.18653/v1/2020.acl-main.475
Bibkey:
Cite (ACL):
Keyon Vafa, Suresh Naidu, and David Blei. 2020. Text-Based Ideal Points. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5345–5357, Online. Association for Computational Linguistics.
Cite (Informal):
Text-Based Ideal Points (Vafa et al., ACL 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.acl-main.475.pdf
Video:
 http://slideslive.com/38929238
Code
 keyonvafa/tbip