Assistant Professor and Faculty Fellow at the NYU Center for Data Science

Mom, you remember I’m a political scientist, right? Well, you know what, things have been changing really fast in our field these last few years because of generative AI and all these computational methods. I’m very optimistic about all the mess that’s going on around us! We can now revisit old theories with a much stronger microscope and pick up subtle patterns in political behavior that older approaches couldn’t see. I’m taking advantage of this brave new world to study how political identity organizes the way people make decisions and, the other way around, how you can take a person’s behavior and work backward to recover what their political identity actually is. My broader agenda is to “embed” political identity inside computer vision tools themselves, so that identity stops being something bolted on after the fact and becomes part of how the model sees behavior from the start. I believe this matters a great deal for computational political science. I’m on the job market this year, wish me luck!

I see my research as situated primarily within the following fields:

Computational Political Behavior (CPB)
Political Communication (PC)
American Politics (AP)

I am on the job market 2026-27

I am currently working on:

Reading Between the Eyes: A Framework for Recovering (Political) Identity from Eye‑Tracking Weak Signal. (AP) (PC) (CPB)

Job Market Paper

I build a classifier that uses computer vision and gaze data to learn political identity from a weak behavioral signal of eye tracking.

Visual Political Polarization (PAP) (AP) (PC) (CPB)

Abstract

Most theories of political polarization assume partisans see the same information and diverge in interpretation. I propose a theory of visual political polarization which holds that part of this divergence may begin in viewing itself, as opposing viewers examine one image differently and those differences also shape what they report. I pretest the theory in a pilot of 608 U.S. adults with two eye-tracking experiments. Under free viewing, a viewer's position divides her attention, evaluations, and emotions (H1). Interrupted political viewing narrowed that distance (H2). Activated political identity changes gaze and leaves responses where they stood (H3). The distance is rebuilt at each viewing, widening and narrowing with its pace (H4). Visual political polarization is therefore a difference a viewer builds during viewing, her position fixing its direction and the extent of her viewing its size. Pilot supplies effect sizes for the preregistered study.

I develop and test a theory of visual political polarization, focusing on how people become polarized through the way they visually perceive the world.

Unpacking the Eye of the Beholder: Social Location, Identity, and the Moving Target of Political Perspectives. (AP) (CPB)

I develop and test a classifier for measuring (political) identity-specific visual sentiment.

Vision and Division: How Partisan Identity Patterns Visual Processing of Political Imagery. (AP) (CPB)

In a large-scale eye-tracking study, we show how motivated visual processing works on partisan divides.

Media Choice and Audience Perceptions: Evidence from Visual Framing of Immigration in News Stories. (AP) (PC) (CPB) published in PLOS ONE

We examine how ideologically different media outlets visually frame immigration and how their audiences are likely to interpret these frames. We show why media bias remains important to study, with visual slant as a central mechanism.

Sounds About Right: Exploring Audio Dramaturgy of Political Propaganda (CPB) (PC)

I introduce the concept of audio dramaturgy in propaganda as the recurring organization of auditory features—such as voice, conversation rhythm, and speaking dynamics—which frames political narratives by consistently pairing specific topics with distinct auditory cues.

The rest is in my CV.