Classifying party affiliation from political speech

Bei Yu, Stefan Kaufmann, Daniel Diermeier

Research output: Contribution to journalArticlepeer-review

76 Scopus citations

Abstract

In this article, we discuss the design of party classifiers for Congressional speech data. We then examine these party classifiers' person-dependency and time-dependency. We found that party classifiers trained on 2005 House speeches can be generalized to the Senate speeches of the same year, but not vice versa. The classifiers trained on 2005 House speeches performed better on Senate speeches from recent years than on older ones, which indicates the classifiers' time-dependency. This dependency may be caused by changes in the issue agenda or the ideological composition of Congress.

Original languageEnglish (US)
Pages (from-to)33-48
Number of pages16
JournalJournal of Information Technology and Politics
Volume5
Issue number1
DOIs
StatePublished - Dec 1 2008
Externally publishedYes

Keywords

  • Evaluation
  • Generalizability
  • Ideology
  • Machine learning
  • Text classification

ASJC Scopus subject areas

  • Computer Science(all)
  • Sociology and Political Science
  • Public Administration

Fingerprint Dive into the research topics of 'Classifying party affiliation from political speech'. Together they form a unique fingerprint.

Cite this