The Digital Docket: Information Retrieval Meets Political Science

Previous research of judicial systems has faced a trade-off between large scale quantitative inquiries focused on readily-counted behaviors, and smaller studies that allow closer examination of legal texts. I will talk about the Digital Docket project, an NSF-funded collaboration between University of Maryland’s Government and Politics Department and the College of Information Studies, which aims to apply techniques from information retrieval and computational linguistics to the study of the U.S. Supreme Court.

By viewing the legal system as an intricate and complex web of communication, the project aims to better understand the role and influences of various actors through analysis of written records. Those records include, for example, briefs written by litigants and other stakeholders, and opinions written by judges and justices. The application of automated content analysis techniques to model the U.S. judicial system represents an opportunity to overcome many of the bottlenecks associated with traditional manual, labor-intensive methods in political science, and also provides a new environment for the advancement of information retrieval and computational linguistic techniques.