Research

I work at the intersection of computational social science and human-AI interaction. My work combines causal inference, large-scale experiments, and human-centered design, with a recurring focus on heterogeneous effects: who benefits from an intervention, who does not, and why.

Algorithmic Interventions & User Agency

How platform mechanisms affect different users differently, and how to give users more control over them.

Wikipedia newcomer mentorship — Causal analysis of 35K+ first conversations showing a mentor's reply raises retention, most for technical questions. → ICWSM 2026
User agency on social media — Heterogeneity analysis of a six-month feed-ranking field experiment, plus a Bluesky tool that lets users personalize feeds toward their own goals.

Human-AI Interaction

How people engage AI for reasoning and participation, and how to design tools that support rather than replace human thinking.

AI and future thinking — Operationalizing "future thinking" (prospection) in human-AI dialogue and detecting it at scale across large conversation datasets.
Human-AI co-writing & attitude change — A multi-agent co-writing system tested in a pre-registered RCT on whether writing a first-person scenario shifts attitudes toward unfamiliar social issues.
AI scaffolding for participation — Lookover, a tool helping students join peer discussion while keeping the thinking their own. → UIST 2026

Machine Learning Foundations

Graph neural networks — DDSM, reframing message passing to mitigate over-smoothing, benchmarked against 15 baselines. → SIGKDD 2025