Classifying Dyads for Militarized Conflict Analysis

Stoehr, Niklas; Hennigen, Lucas Torroba; Ahbab, Samin; West, Robert; Cotterell, Ryan

doi:10.48550/arxiv.2109.12860

Search citation statements

Order By: Relevance

Paper Sections

Select...

Related Work1

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2022

Publication Types

Select...

Other1

Relationship

Self Cite0

Independent1

Authors

Journals

Cited by 1 publication

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite political science research directly linking cosponsorship to the texts of bills and speeches in congress, cosponsorship has so far received little to no attention from the NLP community. However, recent advances of natural language processing [10,38,47,56] provides tools to address numerous social science questions related to legal [45,46,53], con icts [9,43] and political studies [14,18,33,39]. Among these studies, the prediction of roll-call votes has received great attention.…”

Section: Related Workmentioning

confidence: 99%

Disentangling Active and Passive Cosponsorship in the U.S. Congress

Russo¹,

Gote²,

Brandenberger³

et al. 2022

Preprint

View full text Add to dashboard Cite

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 di erent 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.

show abstract