Serina Chang

Serina Chang is an Assistant Professor at the University of California, Berkeley, jointly appointed in Electrical Engineering and Computer Sciences (EECS) and Computational Precision Health, with affiliations to the Berkeley AI Research (BAIR) Lab. Her research addresses AI for public health, focusing on human behavior modeling, network inference, and policy decision support.

• PhD in Computer Science from Stanford University (2024)
• Postdoctoral research in Microsoft Research's Computational Social Science group

Her work spans three thematic areas: inferring human behaviors from novel data sources (search logs, mobility data), simulating behaviors with LLMs for public health applications, and AI-driven policy support through models for vaccine distribution, epidemic forecasting, and equity-focused reopening strategies. She has pioneered AI models using anonymized mobility data to analyze socioeconomic disparities in pandemic impacts.

Recent publications highlight cross-disciplinary innovations:

• Nature (2025) perspective on AI for infectious disease modeling
• ACL 2025 work on human-AI interaction evaluation
• ICWSM 2025 paper demonstrating LLM capabilities in network generation

Scientific recognition includes:

• Google Research Scholar Award (2025)
• NSF Graduate Fellowship (2024)
• KDD Dissertation Award (2025)
• Meta PhD Fellowship (2023)

She advises PhD students in EECS and Computational Precision Health, emphasizing skills in ML research, interdisciplinary collaboration, and real-world impact. Her lab integrates computational methods with public health practice through partnerships with WHO, Chan Zuckerberg Biohub, and United Nations Development Programme.

Current teaching includes CS 294-286: Machine Learning & Human Behavior. She explicitly invites students with interests in AI, human behavior, network science, and public health applications to apply for PhD advising.