Three Cheers For Partisanship: Lexical Framing and Applause in U.S. Presidential Primary Debates

Abstract

Polarization in American politics is at its highest levels in recent history. This polarization can be observed not only in the behaviors of citizens and the politicians who represent them, but also in the rhetoric that politicians use and the reactions of voters to that rhetoric. In this work, I study the language used by candidates in presidential primary debates, and consider the audience's applause (or lack thereof) as a measure of the success of such language. I hypothesize that applause is more likely to occur when the language being used is highly polarized. While previous analyses of voter-directed speech have focused largely on rhetorical structure, this study examines the semantic content of applause-generating language through the automatic discovery of issue-specific lexical framing strategies. Specifically, I present an analysis that 1) models the topics present in a corpus of 104 primary debates, 2) quantifies the party polarization of the language used to discuss those topics, and 3) measures the association between audience applause and topic-specific party polarization. While the relationship is more pronounced for some issues than for others, the results of the analysis lend strong support to the hypothesis that applause is significantly and positively associated with polarity.