Abstract

Using data from 1946–2014, we show that audio features of lawyers’ introductory statements improve the performance of the best prediction models of Supreme Court outcomes. We infer voice attributes using a 15-year sample of human-labeled Supreme Court advocate voices. Audio features improved prediction of case outcomes by 1.1 percentage points. Lawyer traits receive approximately half the weight of the most important feature from the models without audio features.

Replaced by

Daniel L. Chen, Yosh Halberstam, Manoj Kumar, and Alan Yu, “Attorney Voice and the U.S. Supreme Court”, 2019in Law as Data: Computation, Text, and the Future of Legal Analysis, Michael Livermore, and Daniel Rockmore (eds.), Santa Fe Institute Press, 2019.