Teacher Artificial Intelligence-Supported Pedagogical Actions in Collaborative Learning Coregulation: A Wizard-of-Oz Study

Orchestrating collaborative learning (CL) is difficult for teachers as it involves being aware of multiple simultaneous classroom events and intervening when needed. Artificial intelligence (AI) technology might support the teachers' pedagogical actions during CL by helping detect students in need and providing suggestions for intervention. This would be resulting in AI and teacher co-orchestrating CL; the effectiveness of which, however, is still in question. This study explores whether having an AI assistant helping the teacher in orchestrating a CL classroom is understandable for the teacher and if it affects the teachers' pedagogical actions, understanding and strategies of coregulation. Twenty in-service teachers were interviewed using a Wizard-of-Oz protocol. Teachers were asked to identify problems during the CL of groups of students (shown as videos), proposed how they would intervene, and later received (and evaluated) the pedagogical actions suggested by an AI assistant. Our mixed-methods analysis showed that the teachers found the AI assistant useful. Moreover, in multiple cases the teachers started employing the pedagogical actions the AI assistant had introduced to them. Furthermore, an increased number of coregulation methods were employed. Our analysis also explores the extent to which teachers' expertise is associated with their understanding of coregulation, e.g., less experienced teachers did not see coregulation as part of a teacher's responsibility, while more experienced teachers did.