Michael James Bommarito II and Daniel Martin Katz, both of the University of Michigan at Ann Arbor, Center for Study of Complex Systems, have posted the slides of their presentation entitled Building the U.S. Supreme Court Disposition Corpus 1791-2009, given at the University of Pennsylvania Computational Linguistics Lunch (CLunch) and the Linguistic Data Consortium (LDC) in January 2010.
The presentation describes the purposes, development, and attributes of the corpus, which includes disposition, voting, and citation data, and full text content of all of the Court’s opinions.
According to the authors, potential applications of the corpus include:
- “Training prediction models
- Understanding judicial behavior
- Evaluating judicial fidelity”
For more information, please see the slides.