The Feedback Loop in Forming and Supporting Student Teams

Forming effective teams for large classes is a challenge for educators due to the complexity of project needs, the diversity of individual characteristics, and the criteria different educators have for forming teams. In previous work, we proposed a decision-theoretic algorithm that achieves competitive benchmarking results while scaling the performance to handle large class sizes and a large number of constraints. The algorithm was embedded in a web tool and piloted in a variety of classes. The variety of interdisciplinary use cases led to additional research activities, such as a new team formation algorithm that maximizes social preferences, a new team formation algorithm that considers diversity and minimizes minority tokenism, analytics to support ongoing monitoring of team health, and preliminary analysis of communication behavioral differences in gender-diverse and racially diverse teams. I will present our work and talk about future studies to examine how team formation strategies are used in the classroom.