Substantively, I study how political attention, affect, and identity fragment — across nations, networks, ideology, and culture.
Methodologically, I build my own instruments as often as I use them, drawing on natural language processing, Bayesian statistics, dynamic networks, qualitative measurement, and machine learning. Recently I have turned that lens on large language models themselves — how they behave when they annotate text to measure theoretical constructs, and how they encode ideology inside their representations.
Alongside the research, I build the communities and programs around it: summer training institutes, workshop series, and data consulting for civic organizations and local institutions.
research · teaching · data · public scholarship · service · now · about
Research
- Attention Segregation — the dissertation: what organizes the segregation of citizens' private information worlds, and how far beyond politics it reaches
- Cross-National Affective Segregation — anti-Americanism in public discourse
- Network Segregation — who talks to whom among transnational epistemic elites, and how networks respond to shocks
- Ideological Segregation — ideological division in legislative speech on technology
- AI Interpretability & Evaluation — validity gaps in LLM annotation, and the political geometry of ideology in models
Currently
- 2026Working papers on the road at ISA, MPSA, PolMeth, APSA, IC2S2, NetSci, and PaCSS — follow along
The longer story — where this work comes from — is on the About page. The full record is in my CV (PDF).