Get out the vote: Determining support or opposition from Congressional floor-debate transcripts

TL;DR

This paper explores how to determine support or opposition in Congressional floor debates by analyzing transcripts and discourse relationships, significantly improving classification accuracy over isolated speech analysis.

Contribution

It introduces a method that leverages discourse relationships in debate transcripts to better identify support or opposition, advancing computational analysis of political speech.

Findings

Incorporating discourse relationships improves classification accuracy.

Using discussion context outperforms analyzing speeches in isolation.

Discourse-aware models significantly enhance support/opposition detection.

Abstract

We investigate whether one can determine from the transcripts of U.S. Congressional floor debates whether the speeches represent support of or opposition to proposed legislation. To address this problem, we exploit the fact that these speeches occur as part of a discussion; this allows us to use sources of information regarding relationships between discourse segments, such as whether a given utterance indicates agreement with the opinion expressed by another. We find that the incorporation of such information yields substantial improvements over classifying speeches in isolation.