Overview

My research agenda serves to explore impactful questions concerning the role of the judicial branch in the American political system, the motivations and subsequent effects of judicial decision-making, and the emerging methodological tools of computational social science - particularly in the realms of natural language processing, data analysis and visualization, and machine learning models. I provide a brief overview of my active research in these fields below, much of which more recently has served to bridge my interests in judicial politics and computational methods.

Under Review

How to Train Your Stochastic Parrot: Large Language Models for Political Texts

Co-Authored with Dr. Joseph Ornstein (University of Georgia) and Elise Blasingame (University of Georgia)

Large language models pre-trained on massive corpora of text from the Internet have transformed the way that computer scientists approach natural language processing over the past five years. But these “foundation models” have yet to see widespread adoption in the social sciences, partly due to their novelty and upfront costs. In this paper, we demonstrate that such models can be effectively applied to a wide variety of text-as-data tasks in political science–including sentiment analysis, ideological scaling, and topic modeling. In a series of pre-registered analyses, this approach outperforms conventional supervised learning methods without the need for extensive data pre-processing or large sets of labeled training data. And performance is comparable to expert and crowd-coding methods at a fraction of the cost. We explore the accuracy-cost tradeoff associated with adding more model parameters, and discuss how best to adapt and validate the models for particular applications.

Download Working Paper

Recommended citation: Ornstein, J. T., Blasingame, E. N., & Truscott, J. S. (2022). How to Train Your Stochastic Parrot: Large Language Models for Political Texts.

Works in Progress

Idea Diffusion and Coalition Building: How Oral Arguments Influence the Language of U.S. Supreme Court Opinions

Co-Authored with Bryce Dietrich (Purdue University) and Maya Sen (Harvard University)

Measuring Judicial Ideology Through Text

Co-Authored with Michael K. Romano (Shenandoah University)

Ideological Congruence and Judicial Departures from the U.S. Courts of Appeals

Co-Authored with Dr. Richard Vining (University of Georgia)

Understanding the Value of Floor Speeches in a Multimedia Environment

Co-Authored with Bryce Dietrich, Myriam Shiran, Jasper Neath, and Ryan Funkhouser (Purdue University)

Amici as Information: Re-Examining the Role of Amicus Curiae in an Information-Bolstering Environment

Co-Authored with Bryce Dietrich (Purdue University)

Predictions as Inference (Working Title)

Co-Authored with Benjamin Johnson (University of Florida) and Logan Strother (Purdue University)

A Multimodal Analysis of Emotional Arousal and Activation in Supreme Court Confirmation Hearings

Co-Authored with Myriam Shiran (Purdue University)