Jie (Sophia) Gao
Jie (Sophia) Gao

Jie (Sophia) Gao

Malone Postdoc Fellow, Johns Hopkins University
@Malone Center for Engineering in Healthcare
@Data Science and AI Institute
@Center for Language and Speech Processing
jgao77(at)jh.edu
Scholar · Twitter · LinkedIn · CV

About

📢 I am on faculty job market, and have made many friends who are also on the market. Feel free to send emails to connect, or to share opportunities as well 🤗

I am currently a Malone Postdoc Fellow at Johns Hopkins University, where I am mentored by Mark Dredze, Ziang Xiao, and Chien-Ming Huang.▸ more

I design and evaluate human-AI systems that help people build human-readable interpretations in subjective tasks where ground truth is limited or absent. I design them along two directions: (1) Bring AI to Humans: integrating AI into workflows to help people perform subjective tasks more effectively (e.g., AI-assisted qualitative analysis, codebase comprehension, developer experience); and (2) Bring Humans to AI: bringing human oversight to autonomous AI systems to ensure they remain trustworthy and responsible (e.g., responsible AI).

Fundamentally, I am fascinated by how people identify patterns and derive reusable principles from messy, ambiguous, and complex situations and phenomena. Text and code are my entry points into them. This is why I am drawn to analytical methods such as thematic analysis, grounded theory, content analysis, and taxonomy building. These methods help people turn complexity into understanding. To achieve this goal, I use human-AI collaboration to make these methods more accessible, simplified, and supported, while keeping human judgment and reasoning.

Research

Understanding Text & Human Analyst-AI Collaboration for Qualitative Analysis

How can AI support, rather than replace, the interpretive labor of reading unstructured text? I design and evaluate systems that help people code qualitative data, build shared meaning in collaborative analysis, and turn raw text into grounded theories, while keeping human judgment central.

Related: CoAIcoder (TOCHI 2023) · CollabCoder (CHI 2024) · Subjective annotation (HCI+NLP Workshop at EMNLP 2025) · MindCoder (Preprint 2025) · mindcoder.ai

Understanding Code & Developer-AI Collaboration for Code Comprehension

Real-world codebases are messy, and newcomers often struggle to build an accurate mental model. I build tools that help developers comprehend unfamiliar code, review AI-generated changes critically, and collaborate with AI assistants in ways that preserve developer judgment.

Related: CodeMap (ICPC 2026, Distinguished Paper)

News

▶ Show older

Travel

▶ Show older