Disentangling Active and Passive Cosponsorship in the U.S. Congress
This work addresses the challenge of understanding legislative behavior for political scientists and policymakers, though it is incremental in applying graph neural networks to a specific domain.
The paper tackled the problem of distinguishing between active and passive cosponsorship in the U.S. Congress by developing a model that learns legislator representations from bill texts and speech transcripts, achieving an F1-score of 0.88 for predicting these cosponsorship types.
In the U.S. Congress, legislators can use active and passive cosponsorship to support bills. We show that these two types of cosponsorship are driven by two different motivations: the backing of political colleagues and the backing of the bill's content. To this end, we develop an Encoder+RGCN based model that learns legislator representations from bill texts and speech transcripts. These representations predict active and passive cosponsorship with an F1-score of 0.88. Applying our representations to predict voting decisions, we show that they are interpretable and generalize to unseen tasks.