The Issue-Adjusted Ideal Point Model
This provides an exploratory window into how legal language correlates with political support for political scientists and analysts.
The researchers tackled the problem of modeling issue-specific voting behavior by developing a model that explores lawmakers' personal voting patterns by issue area, showing improvement in heldout prediction performance across 12 years of legislative data.
We develop a model of issue-specific voting behavior. This model can be used to explore lawmakers' personal voting patterns of voting by issue area, providing an exploratory window into how the language of the law is correlated with political support. We derive approximate posterior inference algorithms based on variational methods. Across 12 years of legislative data, we demonstrate both improvement in heldout prediction performance and the model's utility in interpreting an inherently multi-dimensional space.