RT Journal Article
SR 00
ID 10.1007/s10657-020-09645-7
A1 Cao, Yu
A1 Ash, Elliott
A1 Chen, Daniel L.
T1 Automated fact-value distinction in court opinions
JF European Journal of Law and Economics
YR 2020
FD 2020-12
VO vol. 50
IS n° 3
SP 451
OP 467
K1 Facts versus law
K1 Law and machine learning
K1 Law and NLP
K1 Text data
AB 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.
SN 0929-1261
LK https://publications.ut-capitole.fr/id/eprint/42842/
UL http://tse-fr.eu/pub/125390