Hi! I'm Hannah Sun, a Master's student in Data Science at the University of Washington.
I am involved in two research labs at the UW iSchool: the
Lab for Computing Cultural Heritage (L4CCH)
and the Language Accessibility Research (LARCH) Lab.
My research is motivated by a central question: How can AI help people interact more
effectively with complex bodies of knowledge? In computational humanities, I investigate
how modern machine learning methods enable scholars to explore large-scale cultural
heritage collections in ways that were previously impractical, revealing patterns,
relationships, and perspectives that complement traditional close reading. In parallel,
my work in human-computer interaction examines how AI can support comprehension of
scientific information through interfaces that help users discover, interpret, and
learn without replacing their own reasoning. Together, these experiences have shaped my
interest in designing human-centered AI systems that augment human inquiry. If our research interests
align, I'd love to connect!
I am currently preparing Ph.D. applications for Fall 2027 and look forward to continuing this
line of research in graduate study.
Summer 2026: I served as a Graduate Research Assistant and project mentor to four undergraduate researchers in the University of Washington's Humanities Data Science Summer Institute (HDSSI), under the supervision of Prof. Benjamin Charles Germain Lee. We worked across two collections curated by the American Institute of Physics, the Emilio Segrè Visual Archives and the Niels Bohr Library Oral History Transcripts. One of our final products was an interactive knowledge graph visualizing the relationships between entities (physicists, laboratories, institutions, etc.) found using GLINER-based named entity recogition and relation extraction. Moving forward, we hope to continue developing the project by more closely connecting the two collections—for example, by linking figures in historical photographs to both named indiviudals and previously unnamed contributors referenced in the oral history transcripts.
Summer 2025: After graduating from the University of Michigan with a B.S. in Data Science, I joined Ternary as a Software Engineer Intern, where I integrated time-series forecasting into the cloud cost prediction API. In September 2025, I started my Master's program in Data Science at the University of Washington.
Publications
Beyond Readability Metrics: Plain Language Priorities in Disability Advocacy Organizations
Proceedings of the 2026 ACM Conference on Fairness, Accountability, and Transparency (FAccT '26), pp. 7864–7892.
Viral Images: Identifying Reprintings within 1.5 Million Photographs in Chronicling America
Submitted to Computational Humanities Research 2027 (CHR 2027).
Experience
Language Accessibility Research (LARCH) Lab
Research Collaborator • Primary Collaborator: Anukriti Kumar • PI: Prof. Lucy Lu Wang
University of Washington • Seattle, WA
Lab for Computing Cultural Heritage (L4CCH)
Research Collaborator • PI: Prof. Benjamin Charles Germain Lee
University of Washington • Seattle, WA
Develop for Good
Program Lead
Remote
Humanities Data Science Summer Institute (AIP Project)
Graduate Research Assistant • PI: Prof. Benjamin Charles Germain Lee
University of Washington • Seattle, WA
Develop for Good (PainUSA Team)
Product Manager
Remote
Ternary
Software Engineer Intern • Supervisor: Kyle Rattet
Remote
University of Michigan Department of Mathematics
Grader, MATH 417: Matrix Algebra I • Supervisor: Prof. Ruiyuan Chen
Ann Arbor, MI
Multidisciplinary Design Program (ProQuest Team)
Student Developer • Mentor: Prof. Sindhu Kutty
University of Michigan • Ann Arbor, MI
Pachira Information Technology
NLP Algorithm Intern • Supervisor: Dr. Chenglong Ma
Zhuhai, China
MobiDrop
Undergraduate Research Assistant • Mentor: Dr. Guantao Zheng
Remote
University of Michigan Math Learning Center
Undergraduate Tutor • Supervisor: Irina Arakelian
Ann Arbor, MI