Text-Based Ideal Points

Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 5345–5357 July 5 - 10, 2020. c⃝2020 Association for Computational Linguistics 5345 Text-Based Ideal Points Keyon Vafa, Suresh Naidu, David M. Blei Columbia University fkeyon.vafa,sn2430,david.bleig@columbia.edu 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 un- supervised probabilistic topic model that ana- lyzes texts to quantify the political positions of its authors. We demonstrate the tbip with two types of politicized text data: U.S. Sen- ate speeches and senator tweets. Though the model does not analyze their votes or politi- cal affiliations, the tbip separates lawmakers by party, learns interpretable politicized top- ics, and infers ideal points close to the classi- cal vote-based ideal points. One benefit of an- alyzing texts, as opposed to votes, is that the tbip can estimate ideal points of anyone who authors political texts, including non-voting ac- tors. To this end, we use it to study tweets from the 2020 Democratic presidential candidates. Using only the texts of their tweets, it identi- fies them along an interpretable progressive-to- moderate spectrum. 1 Introduction Ideal point models are widely used to help char- acterize modern democracies, analyzing lawmak- ers’ votes to estimate their positions on a political spectrum (Poole and Rosenthal, 1985). But votes aren’t the only way that lawmakers express political preferences—press releases, tweets, and speeches all help convey their positions. Like votes, these signals are recorded and easily collected. This paper develops the text-based ideal point model (tbip), a probabilistic topic model for ana- lyzing unstructured political texts to quantify the political preferences of their authors. While classi- cal ideal point models analyze how different people vote on a shared set of bills, the tbip analyzes how different authors write about a shared set of latent topics. The tbip is inspired by the idea of political framing: the specific words and phrases used when discussing a topic can convey political messages (Entman, 1993). Given a corpus of political texts, the tbip estimates the latent topics under discus- sion, the latent political positions of the authors of texts, and how per-topic word choice changes as a function of the political position of the author. A key feature of the tbip is that it is unsupervised. It can be applied to any political text, regardless of whether the authors belong to known political parties. It can also be used to analyze non-voting actors, such as political candidates. Figure 1 shows a tbip analysis of the speeches of the 114th U.S. Senate. The model lays the sen- ators out on the real line and accurately separates them by party. (It does not use party labels in its analysis.) Based only on speeches, it has found an interpretable spectrum—Senator Bernie Sanders is liberal, Senator Mitch McConnell is …

Content truncated to 500 words