We design and study inclusive and immersive e-learning environments that promote engaging and effective learning interactions for a diversified learner population. The project of MILE ("Mixed-Reality-Integrated Learning Environment") studies the design model and effects of an AI-infused, virtual world-based training platform to support responsive teaching practice for preservice teachers and STEM graduate teaching assistants.
Building on MILE, EVE extends this work into real-time 3D simulations where learners practice complex professional interactions with AI-powered virtual agents. The platform supports embodied practice, administrator oversight, structured tasks, and reflection on how instructional or professional decisions affect virtual agents' cognitive and affective states.
Sub-Projects
EVE for Nursing
Uses simulation-based learning to support nursing education scenarios where learners can practice communication, decision-making, debriefing, and patient-centered care in a controlled virtual environment.
EVE for Pre-Service Teachers
Provides preservice teachers with an immersive classroom simulation where they interact with AI-powered virtual students, practice responsive teaching, and observe how instructional moves shape student states over time.
EVE for Neurodivergence
Explores inclusive virtual learning and practice environments for neurodivergent learners, with attention to accessibility, social interaction, representational flexibility, and adaptive supports.
Team Members
Rosalyn Shin
Emily Li
Nuodi Zhang
GEAR
Our research of digital game-based learning focuses on using an integrative approach to design and examine scalable game and participatory simulation based learning systems that comprise learning-oriented game mechanics, design-based pedagogy, data-driven knowledge tracing, and adaptive learner support. Current projects include: "E-Rebuild" - Mathematical Thinking and Learning via Architectural Design and Modeling (Ke as PI, Funded by National Science Foundation, Grant #1318784; Grant #1720533), Virtual-Reality-Based Social and Cognitive Skills Training for Children with High Functioning Autism (Ke as PI, Funded by Spencer Foundation, Grant #201400178; National Science Foundation, Grant #1837917), and Game-based Assessment and Support of STEM-related Competencies and Interest (Ke as Co-PI, Funded by National Science Foundation, Grant #1628937).
Human-AI Collaborative Qualitative Coding
This branch studies how researchers can work with AI systems during qualitative analysis while preserving interpretive rigor, transparency, and human judgment. The work includes workflows for thematic analysis, coding support, researcher reflection, and evaluation of AI-assisted qualitative research tools.
Sub-Projects
Examines LLM-supported thematic analysis workflows for complex qualitative datasets.
Studies where large language models help or hinder qualitative coding, including researcher control, transparency, and interpretive quality.