On the 28th of April Kexin „Bella“ Yang has been invited to present the topic „Human-AI Co-orchestration of Dynamic Transitions between Individual and Collaborative Learning“ at CAIS.
Enabling students to dynamically transition between individual and collaborative learning activities has great potential to support better learning. We explore how technology can support teachers in orchestrating dynamic transitions during class. I have surveyed 54 teachers‘ preferences and boundaries in their co-orchestration preferences, simulated pairing policies performance using historical data to predict its feasibility in actual classroom. In a recent classroom study, working with five teachers and 199 students over 22 class sessions, we conducted classroom-based prototyping of a co-orchestration technology ecosystem that supports the dynamic pairing of students working with intelligent tutoring systems. We discover a potential tension between teachers’ and students’ preferred level of control: students prefer a degree of control over the dynamic transitions that teachers are hesitant to grant. Our study reveals design implications and challenges for future human-AI co-orchestration in classroom use, bringing us closer to realizing the vision of highly-personalized smart classrooms that address the unique needs of each student.
About Kexin:
Kexin „Bella“ Yang is a 3rd-year PhD student in Human-Computer Interaction, at Carnegie Mellon University. She works closely with Prof. Vincent Aleven, Nikol Rummel and Kenneth Holstein. Her research aims to design data-driven human-AI algorithmic systems for smart classrooms of the future, that 1) respect stakeholders’ (teachers and students) boundaries, agency, and preferences, 2) augment teachers’ abilities to distribute their limited attention to where it is needed the most, and 3) achieve effective, self-paced personalized learning that suit students’ individual needs. She worked on and is broadly interested in social computing (e.g., crowdsourcing), XR, robotics, NLP, and their application in education.
Methodology-wise, she uses qualitative, quantitative, and human-centered design research methods, including surveys, interviews, prototyping, focus groups, participatory design, field testing, AB testing, log-data analysis, statistical modeling and experiment design.
She published and presented first-authored papers in HCI and education venues including CHI, CSCW, AIED, EDM and EC-TEL.
Themes: Human-AI interaction, Computer-Supported Collaborative Learning, Education in K-12 Classrooms, XR, Crowdsourcing in Education