tailieunhanh - Báo cáo khoa học: "Historical Analysis of Legal Opinions with a Sparse Mixed-Effects Latent Variable Model"

We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata, and the interactions between the components in metadata, in a general 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 different regions | Historical Analysis of Legal Opinions with a Sparse Mixed-Effects Latent Variable Model William Yang Wang1 and Elijah Mayfield1 and Suresh Naidu2 and Jeremiah Dittmar3 1 School of Computer Science Carnegie Mellon University 2Department of Economics and SIPA Columbia University 3American University and School of Social Science Institute for Advanced Study ww elijah @ sn2430@ dittmar@ Abstract We propose a latent variable model to enhance historical analysis of large corpora. This work extends prior work in topic modelling by incorporating metadata and the interactions between the components in metadata in a general 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 different regions. Because this is a longitudinal data set we are also interested in understanding how these opinions change over the course of decades. We show that the joint learning scheme of our sparse mixed-effects model improves on other state-of-the-art generative and discriminative models on the region and time period identification tasks. Experiments show that our sparse mixed-effects model is more accurate quantitatively and qualitatively interesting and that these improvements are robust across different parameter settings. 1 Introduction Many scientific subjects such as psychology learning sciences and biology have adopted computational approaches to discover latent patterns in large scale datasets Chen and Lombardi 2010 Baker and Yacef 2009 . In contrast the primary methods for historical research still rely on individual judgement and reading primary and secondary sources which are time consuming and expensive. Furthermore traditional human-based methods might have good precision when searching for relevant information but suffer from low recall. Even when .