University of Twente Student Theses

Login

Conversational Agent for Online Collaborative Learning: Facilitating Productive Discussions

Martens, J. (2025) Conversational Agent for Online Collaborative Learning: Facilitating Productive Discussions.

[img] PDF
5MB
Abstract:Collaborative learning is an effective way for students to actively learn and thereby gain a deeper understanding of a specific topic, but it can be difficult for educators to monitor these discussions. This study investigates the effectiveness of Clair, an AI-powered conversational agent, in facilitating productive discussions during collaborative learning tasks. Clair uses the Academically Productive Talk (APT) framework, which includes specific "talk moves" designed to encourage students to share their thoughts, listen to each other, deepen their reasoning, and engage with others’ ideas on the basis of Michaels and O’Connor’s (2015) Four Goals for Productive Discussions (FGPD). In this study, 34 participants completed two discussion tasks: one without Clair and one with Clair's guidance. The results showed that Clair significantly increased deeper reasoning (G3) during discussions and helped improve productivity overall. Certain talk moves, like "Expand Reasoning" and "Recapping", were especially effective at encouraging deeper engagement and balancing contributions between participants. This research identified that Clair has the potential to support educators by improving the quality of collaborative discussions by guiding students. Future research should investigate how Clair can be implemented in real classrooms over time and assess its impact on students' learning outcomes.
Item Type:Essay (Master)
Faculty:BMS: Behavioural, Management and Social Sciences
Programme:Psychology MSc (66604)
Link to this item:https://purl.utwente.nl/essays/105217
Export this item as:BibTeX
EndNote
HTML Citation
Reference Manager

 

Repository Staff Only: item control page