Serina Chang

Research

Some research directions I'm currently excited about include (but are not limited to):

1) Inferring networks & behaviors from novel data sources. How do we infer hard-to-observe behaviors from novel data sources? How do we leverage aggregated or unlabeled data, balance privacy needs, and validate our inferences?
Examples: inferring mobility networks from location data + modeling COVID-19 spread (Nature'21, ICML'24), estimating vaccine uptake and hesitancy from anonymized search logs (Nature Comm'24), measuring polarization and immigration attitudes from political speeches (PNAS'22).

2) Simulating behaviors with LLMs. How do we simulate behaviors at all scales, from individual responses to society-level simulations? How do we validate simulations and address challenges, such as realism, diversity, bias, generalization, and simulation costs? How should we integrate simulators into real-world pipelines (eg, survey studies, AI evaluation) to improve on status quo?
Examples: generating social networks with LLMs (preprint), simulating public opinion with fine-tuning (ongoing), simulating generative AI users for better evaluation (ongoing).

3) Supporting policy and public health with AI. How can AI help to guide more effective and equitable decision-making? How do we translate scientific advances into real-world decision-support tools?
Examples: deploying reopening dashboard for Virginia Department of Health (KDD'21), delivering vaccine site recommendations (IAAI'22), estimating pandemic policy spillover effects (AAAI'23), collaboration with United Nations Development Programme (ongoing).

Advising

I am recruiting PhD students this cycle, to start in Fall 2025! I can advise students in EECS or Computational Precision Health (CPH). Applications are open for both programs: see here. Please read on if you're interested in working together...

Instructions for applicants
I am interested in working with students from a variety of backgrounds, and I value both personal and professional diversity. I'm generally interested in students who are skilled in ML and data science, care deeply about real-world impact and interdisciplinary work, have strong critical thinking and problem-solving skills, and are clear communicators. A strong research fit is also important, such as interests in AI for public health, computational social science, networks/graphs, or any of the research directions described above.

I'll try to review all applications in related areas, but given the volume of applications, including my name makes it much likelier that your application will be flagged to me.

If you are applying for EECS: (1) when entering your faculty preference on the application, write in my name in the free text box below the dropdowns (see instructions regarding new faculty on the EECS Admissions page), (2) include my name in your Statement of Purpose.
If you are applying for CPH: (1) when entering your faculty preference on the application, write in my name for one of the "Faculty Preference" text boxes, (2) include my name in your Statement of Purpose. I will also be paying special attention to applications that select "Community and Public Health" under Health Research Topics.

Selected Papers

Please see my CV for a full list of papers.

LLMs generate structurally realistic social networks but overestimate political homophily
Serina Chang*, Alicja Chaszczewicz*, Emma Wang, Maya Josifovska, Emma Pierson, and Jure Leskovec
Presented at IC2S2 2024 as Plenary Talk (2.8% submissions)
[paper] [code]

Measuring vaccination coverage and concerns of vaccine holdouts from web search logs
Serina Chang, Adam Fourney, and Eric Horvitz
Nature Communications 2024
Also presented at KDD 2023 Workshop on Epidemiology Meets Data Mining and Knowledge Discovery (oral) and KDD 2023 Workshop on Data Science for Social Good (oral)
[paper] [data & code]

Inferring dynamic networks from marginals with iterative proportional fitting
Serina Chang*, Frederic Koehler*, Zhaonan Qu*, Jure Leskovec, and Johan Ugander
ICML 2024
Also presented at Learning on Graphs 2023 (extended abstract)
[paper] [code]

Estimating geographic spillover effects of COVID-19 policies from large-scale mobility networks
Serina Chang, Damir Vrabac, Jure Leskovec, and Johan Ugander
AAAI 2023
Also presented at KDD 2022 Workshop on Data-driven Humanitarian Mapping and Policymaking (oral) and IC2S2 2022
[paper] [code]

Computational analysis of 140 years of US political speeches reveals more positive but increasingly polarized framing of immigration
Dallas Card, Serina Chang, Chris Becker, Julia Mendelsohn, Rob Voigt, Leah Boustan, Ran Abramitzky, and Dan Jurafsky
PNAS 2022
Article in Stanford HAI News by Edmund L. Andrews
[paper] [code]

Supporting COVID-19 policy response with large-scale mobility-based modeling
Serina Chang, Mandy L. Wilson, Bryan Lewis, Zakaria Mehrab, Komal K. Dudakiya, Emma Pierson, Pang Wei Koh, Jaline Gerardin, Beth Redbird, David Grusky, Madhav Marathe, and Jure Leskovec
KDD 2021, Applied Data Science Track - Best Paper Award
[paper] [code] [blog post]

Mobility network models of COVID-19 explain inequities and inform reopening
Serina Chang*, Emma Pierson*, Pang Wei Koh*, Jaline Gerardin, Beth Redbird, David Grusky, and Jure Leskovec
Nature 2021
Commentary in Nature News and Views by Kevin Ma and Dr. Marc Lipsitch
Interactive article in The New York Times by Yaryna Serkez
Selected media coverage: The New York Times, The Washington Post, Bloomberg, CNN, Wired, MIT Technology Review, and Stanford Press
Also presented at Networks 2021 (oral), NeurIPS 2020 Workshop on Machine Learning for Health, NeurIPS 2020 COVID-19 Symposium, and OECD-ODISSEI Webinar on Open Data Infrastructure
[paper] [code] [talk] [website]

Automatically inferring gender associations from language
Serina Chang and Kathleen McKeown
EMNLP 2019 (short paper, oral)
[paper] [code] [talk]

Detecting gang-involved escalation on social media using context
Serina Chang, Ruiqi Zhong, Ethan Adams, Fei-Tzin Lee, Siddharth Varia, Chris Kedzie, Desmond Patton, William Frey, and Kathleen McKeown
EMNLP 2018 (long paper, oral)
[paper] [code] [talk]

Serina Chang

Recent News