free web templates

Photo credit: Aurora Brachman

serinac@cs.stanford.edu
[CV] [Bio] [Google Scholar] [Twitter]

Serina Chang

I am currently a PhD candidate in Computer Science (CS) at Stanford University, advised by Prof. Jure Leskovec and Prof. Johan Ugander. Previously, I completed my undergrad at Columbia University, where I studied CS and Sociology, and was advised by Prof. Kathy McKeown. I am fortunate to be supported by the NSF Graduate Research Fellowship and the Meta PhD Fellowship. I am on the academic job market for 2023-2024.

My research develops computational methods to tackle complex societal challenges, from pandemics to polarization to supply chains. I leverage novel data sources - such as cell phones, search logs, and social media - to understand human networks and behaviors at the center of such challenges. These data sources provide new opportunities to capture individuals at scale, with the potential to improve decisions that affect billions every day.

However, novel data also introduces challenges for analysis, such as how to infer fine-grained networks from aggregated data (Nature'21), how to estimate causal spillover effects of policies (AAAI'23), and how to derive meaning from vast unlabeled data such as search logs (arXiv'23), speeches (PNAS'22), news articles (EMNLP'19), and social media (EMNLP'18). To address these challenges, my research develops new methods blending machine learning, network science, and statistics. I use these methods to develop policy insights and build decision-support tools (KDD'21, IAAI'22), which have been widely cited and used by policymakers.

Recent News

Papers

* indicates co-first authorship

Inferring networks from marginals using iterative proportional fitting
Serina Chang*, Zhaonan Qu*, Jure Leskovec, and Johan Ugander
Under review


Accurate measures of vaccination and concerns of vaccine holdouts from web search logs
Serina Chang, Adam Fourney, and Eric Horvitz
Under review
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]


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]


To recommend or not? A model-based comparison of item-matching processes
Serina Chang and Johan Ugander
ICWSM 2022
Also presented at IC2S2 2021 (oral)
[paper] [code]


Data-driven real-time strategic placement of mobile vaccine distribution sites
Zakaria Mehrab, Mandy L. Wilson, Serina Chang, Galen Harrison, Bryan L. Lewis, Alex Tellionis, Justin Crow, Dennis Kim, Scott Spillman, Kate Peters, Jure Leskovec, and Madhav Marathe
IAAI 2022
[paper]


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]


Epidemic dynamics in inhomogeneous populations and the role of superspreaders
Kyle Kawagoe*, Mark Rychnovsky*, Serina Chang, Greg Huber, Lucy M. Li, Jonathan Miller, Reuven Pnini, Boris Veytsman, and David Yllanes
Physical Review Research 2021
[paper]


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]


Crowd-sourced iterative annotation for narrative summarization corpora
Jessica Ouyang, Serina Chang, and Kathleen McKeown
EACL 2017 (short paper, oral)
[paper] [video]

Work Experience

Microsoft, Research Intern
(2022-2023)

Internship with Dr. Eric Horvitz. Developed methods in graph ML to detect vaccination intent and analyze vaccine concerns in large-search search logs. See Chang, Fourney, and Horvitz, "Accurate Measures of Vaccination and Concerns of Vaccine Holdouts from Web Search Logs."

Stanford, Machine Learning with Graphs (CS224W), Head CA (2021)

Managed team of course assistants and class of over 300 students. This course, taught by Prof. Jure Leskovec, covers the foundations and state-of-the-art of graph ML, including graph neural networks, representation learning, and reasoning over knowledge graphs.

Google, Software Engineering Intern (2018)

Built a user-facing feature for Google Search and Assistant. Designed new logic to parse natural language queries related to the feature, implemented backend in Search architecture, and worked with UX designer and Product Manager to create frontend.

Leadership & Innovation

Lean In at Columbia
Co-President (2017-2018); Senior Advisor (2018-2019)

As Co-President, I revamped our program to focus on our members' professional and personal growth in the context of intersectional experiences, such as being LGBTQ or interdisciplinary. With my Co-President Kara Schechtman and our Board, we quintupled the size of our membership and founded a mentorship program, which matched over 70 students to NYC professionals in its first year. We also founded the Lean In @ CU Conference, a day-long event celebrating mentorship and different paths of feminism.


Columbia Womxn in CS (WiCS)
Academic Chair (2017-2019)

I founded WiCS Lightning Talks, a new speaker series at Columbia featuring student researchers with a focus on supporting traditionally underrepresented groups in CS. The series empowers student researchers by giving them the opportunity to present their work, and, in turn, inspires their peers to dive into research. As Academic Chair, I also organized panels with CS faculty at Columbia, and participated as a mentor in WiCS' Coffee Chats program.


Intercollegiate Chamber Music Festival (ICMF)
Co-Founder; Producer (2017-2019)

I co-founded this initiative while serving as Co-President of Columbia Classical Performers. Along with my Co-President Cindy Liu and Vice President Dean Deng, we founded ICMF in collaboration with The Chamber Music Society of Lincoln Center. The festival celebrates collegiate chamber ensembles, providing them opportunities to perform at Lincoln Center and to particpate in master classes with world-renowned artists.

Classical Music
Here are some of my favorite performances! Check out my YouTube channel for more.

C. Saint-Saëns, Piano Trio No.2 in E Minor, Op.92

Jason Shu (violin), Elena Ariza (cello), and Serina Chang (piano). Coached by Muneko Otani. 

N. Kapustin, Variations, Op.41

Serina Chang (piano). Student of Elena Belli.

L. Bernstein, arranged by J. Musto, Symphonic Dances from West Side Story

Alison Chang (piano) and Serina Chang (piano). Coached by Yegor Shevtsov. 

© Serina Chang 2023