Predicting Legislative Roll Calls from Text
نویسندگان
چکیده
We develop several predictive models linking legislative sentiment to legislative text. Our models, which draw on ideas from ideal point estimation and topic models, predict voting patterns based on the contents of bills and infer the political leanings of legislators. With supervised topics, we provide an exploratory window into how the language of the law is correlated with political support. We also derive approximate posterior inference algorithms based on variational methods. Across 12 years of legislative data, we predict specific voting patterns with high accuracy.
منابع مشابه
An Embedding Model for Predicting Roll-Call Votes
We develop a novel embedding-based model for predicting legislative roll-call votes from bill text. The model introduces multidimensional ideal vectors for legislators as an alternative to single dimensional ideal point models for quantitatively analyzing roll-call data. These vectors are learned to correspond with pre-trained word embeddings which allows us to analyze which features in a bill ...
متن کاملWhy Roll Calls? a Model of Position-taking in Legislative Voting and Elections
We develop a rationale for position-taking preferences in legislatures using a formal model of legislative vote-buying and elections. In our model, citizens and an interest group are motivated by policy, while legislators are motivated by holding office. The group may attempt to buy legislators’ votes by offering contracts based on their votes. If citizens cannot condition their re-election vot...
متن کاملRebels with a Cause?
Does a Member of the British Parliament’s voting record have any effect on their constituency electoral performance? Scholars have assumed not, else they have tested the proposition with an extremely limited number of roll calls. Congruent with public opinion findings we contend that, paradoxically, voters conditionally reward both ‘party unity’ and ‘independent mindedness’ in their elected rep...
متن کاملWhere You Sit is Where You Stand: The Impact of Seating Proximity on Legislative Cue-Taking∗
This article builds on Matthews and Stimson’s (1975) study of legislative cuetaking, analyzing the extent to which legislators sitting next to each other influence each others’ voting behavior. Data come from three decades of roll call votes in the California Assembly, a chamber in which each member is paired with a deskmate. By comparing deskmate pairs with nondeskmate pairs, I find that legis...
متن کاملHow a Bill Becomes a Law - Predicting Votes from Legislation Text
Thanks to the efforts of organizations like GovTrack (Tauberer, 2012), a tremendous amount of roll-call and bill-text data has become available over the past few years. At the same time, most analyses are based on idealpoint models that use only the votes themselves in modelling voting decisions, and ignore bill text. We analyze a variety of models for predicting the outcomes of roll-call votes...
متن کامل