TY  - JOUR
ID  - publications42842
UR  - http://tse-fr.eu/pub/125390
IS  - n° 3
A1  - Cao, Yu
A1  - Ash, Elliott
A1  - Chen, Daniel L.
Y1  - 2020/12//
N2  - 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.
JF  - European Journal of Law and Economics
VL  - vol. 50
KW  - Facts versus law
KW  - Law and machine learning
KW  - Law and NLP
KW  - Text data
SN  - 0929-1261
TI  - Automated fact-value distinction in court opinions
SP  - 451
AV  - none
EP  - 467
ER  -