The Promise and Pitfalls of Automated Text-Scaling Techniques for the Analysis of Jurisprudential Change

Dyevre, A. (2020). The promise and pitfall of automated text-scaling techniques for the analysis of jurisprudential change. Artificial Intelligence and Law, 1-31.

33 Pages Posted: 3 Jul 2015 Last revised: 27 Aug 2020

See all articles by Arthur Dyevre

Arthur Dyevre

KU Leuven Centre for Empirical Jurisprudence

Date Written: March 14, 2019

Abstract

I consider the potential of eight text-scaling methods for the analysis of jurisprudential change. I use a small corpus of well-documented German Federal Constitutional Court opinions on European integration to compare the machine-generated scores to scholarly accounts of the case law and legal expert ratings. Naive Bayes, Word2Vec, Correspondence Analysis and Latent Semantic Analysis appear to perform well. Less convincing are the performance of Wordscores, ML Affinity and lexicon-based sentiment analysis. While both the high-dimensionality of judicial texts and the validation of computer-based jurisprudential estimates pose major methodological challenges, I conclude that automated text-scaling methods hold out great promise for legal research.

Keywords: Judicial Opinions, Jurisprudential Change, Automated Text-scaling

Suggested Citation

Dyevre, Arthur, The Promise and Pitfalls of Automated Text-Scaling Techniques for the Analysis of Jurisprudential Change (March 14, 2019). Dyevre, A. (2020). The promise and pitfall of automated text-scaling techniques for the analysis of jurisprudential change. Artificial Intelligence and Law, 1-31., Available at SSRN: https://ssrn.com/abstract=2626370 or http://dx.doi.org/10.2139/ssrn.2626370

Arthur Dyevre (Contact Author)

KU Leuven Centre for Empirical Jurisprudence ( email )

Tiensestraat 41
Leuven, B-3000
Belgium
+32492971322 (Phone)

HOME PAGE: http://www.arthurdyevre.org

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
249
Abstract Views
1,299
rank
172,096
PlumX Metrics