Abstract

Unstructured data is pervasive in our daily lives, appearing in forms such as meeting and interview transcripts, written notes, and social media posts. These data often contain valuable human knowledge and insights. To uncover them, researchers have traditionally relied on qualitative analysis, a foundational method widely applied across disciplines such as computer science, social science and psychology. However, this approach typically involves multiple manual steps, including open coding, grouping codes, and identifying themes, which are time-consuming and labor-intensive, thereby limiting scalability and generalizability. With the advancement of AI technologies such as LLMs, this foundational methodology has undergone a fundamental paradigm shift—from traditional manual work to the integration of AI technologies. In this talk, Jie Gao will present her research, spanning from the initial identification of computational opportunities to the design, development, and evaluation of AI workflows and tools. Her work not only leverages automation but also focuses on designing novel human–AI collaboration. As one of the earliest researchers deeply grounded in computer-assisted qualitative analysis, even before LLMs became popular, her work in recent years has advanced and contributed to the fundamental methodological paradigm shift. Moreover, her research on these workflows has also inspired practical tools that can be directly used by end users.

 Bio

Jie Gao is a Malone Postdoctoral Fellow in the School of Computer Science, Malone Center for Engineering in Healthcare and Center for Language and Speech Processing, working with Mark Dredze, Ziang Xiao, and Chien-Ming Huang. Previously, she was a postdoctoral researcher with the Mens, Manus, and Machina (M3S) team at the Singapore-MIT Alliance for Research and Technology. She earned her PhD in Information Systems Technology and Design at the Singapore University of Technology and Design in 2024. Her research interests include human–AI collaboration, computational social science, and human-centric software engineering. More specifically, she focuses on advancing fundamental methodologies across these domains, such as qualitative data analysis, by building, theorizing, and evaluating innovative human-centered AI workflows and tools. Her work has been published in top-tier HCI venues, including CHI, TOCHI, UIST, and UbiComp. She has also served as an Associate Chair for CHI 2025–2026 and for CHI 2022–2023 Late-Breaking Work Track, and she actively contributes to the community as reviewers for CHI, CSCW, UIST, International Journal of Human–Computer Interaction, ACM Transactions on Interactive Intelligent Systems, Computers in Human Behavior, etc.