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 not allowing for generalization across sessions. In this paper, we show that text alone is insufficient for modeling voting outcomes in new contexts, as session changes lead to changes in the underlying data generation process. We propose a novel neural method for encoding documents alongside additional metadata, achieving an average of a 4% boost in accuracy over the previous state-of-the-art.

Modeling U.S. Congressional legislation and roll-call votes has received significant attention in previous literature, and while legislators across 50 state governments and D.C. propose over 100,000 bills each year, enacting over 30% of them on average, state level analysis has received relatively less attention due in part to the difficulty in obtaining the necessary data. Since each state legislature is guided by their own procedures, politics and issues, however, it is difficult to qualitatively asses the factors that affect the likelihood of a legislative initiative succeeding. We present several methods for modeling the likelihood of a bill receiving floor action across all 50 states and D.C. We utilize the lexical content of over 1 million bills, along with contextual legislature and legislator derived features to build our predictive models, allowing a comparison of what factors are important to the lawmaking process. Furthermore, we show that these signals hold complementary predictive power, together achieving an average improvement in accuracy of 18% over state specific baselines.