Search for: All records

Abstract We implemented a user-centered approach to the design of an artificial intelligence (AI) system that provides users with access to information about the workings of the United States federal court system regardless of their technical background. Presently, most of the records associated with the federal judiciary are provided through a federal system that does not support exploration aimed at discovering systematic patterns about court activities. In addition, many users lack the data analytical skills necessary to conduct their own analyses and convert data into information. We conducted interviews, observations, and surveys to uncover the needs of our users and discuss the development of an intuitive platform informed from these needs that makes it possible for legal scholars, lawyers, and journalists to discover answers to more advanced questions about the federal court system. We report on results from usability testing and discuss design implications for AI and law practitioners and researchers. 

The docket sheet of a court case contains a wealth of information about the progression of a case, the parties’ and judge’s decision-making along the way, and the case’s ultimate outcome that can be used in analytical applications. However, the unstructured text of the docket sheet and the terse and variable phrasing of docket entries require the development of new models to identify key entities to enable analysis at a systematic level. We developed a judge entity recognition language model and disambiguation pipeline for US District Court records. Our model can robustly identify mentions of judicial entities in free text (~99% F-1 Score) and outperforms general state-of-the-art language models by 13%. Our disambiguation pipeline is able to robustly identify both appointed and non-appointed judicial actors and correctly infer the type of appointment (~99% precision). Lastly, we show with a case study on in forma pauperis decision-making that there is substantial error (~30%) attributing decision outcomes to judicial actors if the free text of the docket is not used to make the identification and attribution.