Party Matters: Enhancing Legislative Embeddings with Author Attributes for Vote Prediction
This work addresses the challenge of vote prediction for political scientists and policymakers by improving generalization across legislative sessions, though it is incremental as it builds on existing methods with metadata integration.
The paper tackled the problem of predicting Congressional legislators' votes across different sessions by showing that metadata, specifically sponsors' ideologies, is crucial for modeling voting outcomes in new contexts. The result was a 4% boost in accuracy over the previous state-of-the-art when augmenting bill text with this metadata in a neural network model.
Predicting how Congressional legislators will vote is important for understanding their past and future behavior. However, previous work on roll-call prediction has been limited to single session settings, thus did not consider generalization across sessions. In this paper, we show that metadata is crucial for modeling voting outcomes in new contexts, as changes between sessions lead to changes in the underlying data generation process. We show how augmenting bill text with the sponsors' ideologies in a neural network model can achieve an average of a 4% boost in accuracy over the previous state-of-the-art.