Paper: Historical Analysis of Legal Opinions with a Sparse Mixed-Effects Latent Variable Model

ACL ID P12-1078
Title Historical Analysis of Legal Opinions with a Sparse Mixed-Effects Latent Variable Model
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2012
Authors

We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by in- corporating metadata, and the interactions be- tween the components in metadata, in a gen- eral way. To test this, we collect a corpus of slavery-related United States property law judgements sampled from the years 1730 to 1866. We study the language use in these legal cases, with a special focus on shifts in opinions on controversial topics across differ- ent regions. Because this is a longitudinal data set, we are also interested in understand- ing how these opinions change over the course of decades. We show that the joint learning scheme of our sparse mixed-effects model im- proves on other state-of-the-art generative and discriminative models on th...