Law Search as Prediction

Abstract

The final version of this paper has been published in Artificial Intelligence and Law 23:3-34 (2021), available at https://link.springer.com/article/10.1007/s10506-020-09261-5.



The process of searching for relevant legal materials is fundamental to legal reasoning. However, despite its enormous practical and theoretical importance, law search has been given inadequate attention by scholars. In this article, we define the problem of law search, examine its normative and empirical dimensions, and investigate one particularly promising computationally based approach. We implement a model of law search based on a notion of search space and search strategies and apply that model to the corpus of U.S. Supreme Court opinions. We test the success of the model against both citation information and hand-coded legal relevance determinations.

Keywords: search, artificial intelligence and law, machine learning, topic models, legal reasoning