Article

Automated fact-value distinction in court opinions

Yu Cao, Elliott Ash et Daniel L. Chen

Résumé

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.

Mots-clés

Facts versus law; Law and machine learning; Law and NLP; Text data;

Codes JEL

  • K40: General

Voir aussi

Publié dans

European Journal of Law and Economics, vol. 50, décembre 2020, p. 451–467