Cao, Yu, Ash, Elliott and Chen, Daniel L. (2020) Automated fact-value distinction in court opinions. European Journal of Law and Economics, vol. 50 (n° 3). pp. 451-467.

Full text not available from this repository.
Identification Number : 10.1007/s10657-020-09645-7


This paper studies the problem of automated classification of fact statements and value statements in written judicial decisions. We compare a range of methods and demonstrate that the linguistic features of sentences and paragraphs can be used to successfully classify them along this dimension. The Wordscores method by Laver et al. (Am Polit Sci Rev 97(2):311–331, 2003) performs best in held out data. In an application, we show that the value segments of opinions are more informative than fact segments of the ideological direction of U.S. circuit court opinions.

Item Type: Article
Language: English
Date: December 2020
Refereed: Yes
Uncontrolled Keywords: Facts versus law, Law and machine learning, Law and NLP, Text data
JEL Classification: K40 - General
Divisions: TSE-R (Toulouse)
Site: UT1
Date Deposited: 19 Mar 2021 09:34
Last Modified: 08 Jun 2023 11:34
OAI Identifier:
View Item