Keywords
Oral Argument, Judicial Decisionmaking, Computational analysis
Abstract
As the first study to leverage modem machine learning techniques to analyze Supreme Court oral argument dialogue, this Article breaks important new ground. Previous empirical studies of oral argument and judicial decision making have been limited to a small number of discrete, quantifiable attributes, many of them external to oral argument. Past work has examined, for instance, the strength of the connection between the Justices' votes and their ideological preferences; variation in the Justices' votes based on the legal subject matter at issue; and the Justices' tendency to ask more and longer questions to the parties they ultimately vote against.
This study breaks through past limitations, borrowing techniques from the fields of artificial intelligence and machine learning to analyze not only counts of questions and ideological leanings, but the actual oral argument dialogue itself-the content of the Justices' questions. In so doing, the Article offers an important new window into aspects of oral argument that have long resisted empirical study, including the Justices' individual questioning styles, how each expresses skepticism, what inter- Justice dialogue looks like for each Justice, and which of the Justices' questions most drive oral argument.
Recommended Citation
Dickinson, Gregory M.
(2019)
"A Computational Analysis of Oral Argument in the Supreme Court,"
Cornell Journal of Law and Public Policy: Vol. 28:
Iss.
3, Article 3.
Available at:
https://scholarship.law.cornell.edu/cjlpp/vol28/iss3/3