Analysis of vocal implicit bias in SCOTUS decisions through predictive modelling

Abstract

Several existing pen and paper tests to measure implicit bias have been found to have discrepancies. This could be largely due to the fact that the subjects are aware of the implicit bias tests and they consciously choose to change their answers. Hence, we've leveraged machine learning techniques to detect bias in the judicial context by examining the oral arguments. The adverse implications due to the presence of implicit bias in judiciary decisions could have far-reaching consequences. This study aims to check if the vocal intonations of the Justices and lawyers at the Supreme Court of the United States could act as an indicator for predicting the case outcome.