Serina Chang

Research Abstract:

My research develops computational methods to tackle complex societal challenges, from pandemics to polarization to supply chains. I leverage novel data sources, such as mobility data and search logs, to capture human networks and behaviors at the center of societal systems. To address challenges that arise from real-world data, I develop new methods blending machine learning, network science, and natural language processing. I use these methods to derive policy insights and build decision-support tools, paving a new way for high-stakes decision-making powered by large-scale computation and data. Specifically, my work has addressed three fundamental data challenges. First, physical human networks are rarely known, but they are essential for downstream policy problems. I have identified novel data sources, such as mobility data, that provide aggregated views of these networks, and developed statistical methods to infer fine-grained networks with local spatiotemporal patterns that greatly impact health outcomes and disparities (Nature, 2021). Second, novel data provides a wealth of new information but is often unlabeled for signals of interest (e.g., user intents). I have built ML systems to efficiently label and organize such data (e.g., into ontologies) while balancing user privacy, such as through anonymized search logs, social media (EMNLP'18), news articles (EMNLP'19), and public speeches (PNAS, 2022). Finally, even when networks are observed, the underlying mechanisms that drive their evolution remain unknown. I have developed methods blending causal inference and graph ML to discover mechanisms driving dynamic networks, such as spillover effects in mobility networks (AAAI'23) and production functions governing supply chains. By addressing these challenges, my research seeks to deliver on the promise of harnessing novel data sources for critical decision-making.

Bio:

Serina Chang is a 5th year PhD student in Computer Science at Stanford University. She develops methods in machine learning and data science to tackle complex societal challenges, from pandemics to polarization to supply chains. Her research focuses on large-scale human networks and novel data sensors, such as mobility networks from location data and query-click graphs from search engines. Her work has been published in venues including Nature, PNAS, KDD, AAAI, EMNLP, and ICWSM, and featured in over 650 news outlets, including The New York Times and The Washington Post. Her work is also recognized by the KDD 2021 Best Paper Award, NSF Graduate Research Fellowship, Meta PhD Fellowship, EECS Rising Stars, Rising Stars in Data Science, Cornell Future Faculty Symposium, and CRA Outstanding Undergraduate Researcher Award. Beyond research, Serina has also served as head course assistant for Stanford’s Machine Learning with Graphs, Program Chair of Machine Learning for Health 2023, and a co-Chair of the Data Science for Social Good Workshop at KDD 2023.