My research generates novel insights about the interplay between data science and politics, and leverages these insights to address critical functions of political institutions. The subject matter is part of the emerging field of computational social science, which combines data science and political science to conduct research at scale.

There are two pillars of my research. First, I experiment with and demonstrate how researchers in the social sciences may use techniques from computer science to make substantive inferences. Second, I apply these techniques to ask and answer questions at the core of modern political behavior. My research falls into three broad categories:

  1. How should we measure political structures with text? Understanding how the latent structures measured by text influence or are influenced by political processes is a natural avenue of inquiry for social scientists. Content analysis techniques from computer science bring great opportunity to the pursuit of such inquiry, but the wholesale importation of them prompts new challenges. Of paramount importance is the challenge of general inference: what may we claim about the fundamental nature of a political process, given the text we observe? My dissertation enhances our ability to make claims by introducing a new method. With the method, researchers may test if their approach to text-based measurement is appropriate before proceeding inference.
  2. How is technology changing the relationship between parties and voters? In a time of increasing partisanship and polarization, it is easy to overlook the fundamental role new technologies play in defining the relationship between parties and voters. New technologies, including depersonalized communication at scale, human–machine interaction, and enhanced prediction have precipitously reduced the costs of voter engagement. Are voters starting to catch on? I argue that as the costs of engagement have decreased, the value of costly signalling has increased; in a world where contact no longer suggests care, voters only respond to interventions where the cost of engagement is perceived to be high.
  3. How can we make political methodology more accessible? My goal is to make the methods and software developed in the course of my research beneficial to as broad of an audience as possible. My recently published open-source computer vision software has seen incredible adoption by researchers developing text corpora (it has been forked and starred more than 99.9% of projects on GitHub). I also help Mentor Collective, an edtech startup in Boston, manage randomized controlled trials studying the effect of educational interventions on student success.

As a result of my work, I hold provisional patents for the reduction and mapping of dimensionality in “big” unstructured datasets and a system and interface for massive-scale, multi-container processing of generative programming to process “big data.” My work received the National Science Foundation’s Honorable Mention in 2017, considered a national honor. I received my M.Phil. and M.A. from Columbia University, and my A.B. from Washington University in St. Louis. Before starting my Ph.D., I worked as a senior director at an industrial text analytics company, and as an advance staffer in the Obama White House.