معرفی
Joel Chan is an Affiliate Assistant Professor in the Department of Computer Science at the University of Maryland, specializing in human-computer interaction and artificial intelligence research with applications in scholarly communication and design innovation. His work bridges computational systems and human cognitive processes to enhance knowledge work.
His research portfolio emphasizes:
- Scholarly sensemaking and knowledge synthesis infrastructure
- Generative AI for hypothesis exploration and analogical reasoning
- Cross-disciplinary translation tools using computational linguistics
- Biologically inspired design systems and creativity support
- Human-AI collaboration in visual data analysis and programming
Recent publications (2023-2025) demonstrate a decisive shift toward integrating large language models into scholarly workflows, particularly for structured hypothesis exploration and cross-domain analogical inspiration. His systems like CausalMapper and AnalogiLead exemplify practical implementations that transform theoretical frameworks into usable tools for researchers and designers.
Building on foundational work in analogical innovation (2010-2022), Chan's research trajectory shows consistent evolution from studying example-based problem-solving to developing AI-augmented environments that mitigate cognitive limitations in complex knowledge tasks, with significant implications for academic practice and creative industries.
