Scaling politically meaningful dimensions using texts and votes

Item response theory models for roll-call voting data provide political scientists with parsimonious descriptions of political actors' relative preferences. However, models using only voting data tend to obscure variation in preferences across different issues due to identification and labeling problems that arise in multidimensional scaling models. We propose a new approach to using sources of metadata about votes to estimate the degree to which those votes are about common issues. We demonstrate our approach with votes and opinion texts from the U.S. Supreme Court, using latent Dirichlet allocation to discover the extent to which different issues were at stake in different cases and estimating justice preferences within each of those issues. This approach can be applied using a variety of unsupervised and supervised topic models for text, community detection models for networks, or any other tool capable of generating discrete or mixture categorization of subject matter from relevant vote-specific metadata.