Predicting legislative roll calls from text
SM Gerrish, DM Blei - … of the 28th International Conference on …, 2011 - oar.princeton.edu
Proceedings of the 28th International Conference on Machine Learning …, 2011•oar.princeton.edu
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 …
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 …
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.
oar.princeton.edu
Showing the best result for this search. See all results