Open access
Date
2020-06Type
- Journal Article
Abstract
This paper draws on machine learning methods for text classification to predict the ideological direction of decisions from the associated text. Using a 5% hand-coded sample of cases from U.S. Circuit Courts, we explore and evaluate a variety of machine classifiers to predict “conservative decision” or “liberal decision” in held-out data. Our best classifier is highly predictive (F1 = .65) and allows us to extrapolate ideological direction to the full sample. We then use these predictions to replicate and extend Landes and Posner’s (2009) analysis of how the party of the nominating president influences circuit judge's votes. Show more
Permanent link
https://doi.org/10.3929/ethz-b-000406465Publication status
publishedExternal links
Journal / series
International Review of Law and EconomicsVolume
Pages / Article No.
Publisher
ElsevierSubject
Judge ideology; Circuit courts; Text data; NLPOrganisational unit
09627 - Ash, Elliott / Ash, Elliott
More
Show all metadata