Productive Discussion Moves in Groups Addressing Controversial Issues

TL;DR

This study addresses how to foster productive dialogue on controversial AI-ethics issues in diverse classrooms. It introduces a hybrid Dialogue-Centric Learning Analytics pipeline, combining expert taxonomy (SEDA) with data-driven clustering (BERTopic) and language embeddings to identify 14 distinct discussion moves across five categories. Using linear mixed-effects modeling and Ordered Network Analysis on 83 sessions, the authors show that Emotive/Experiential Arguments and Acknowledging Ambiguity positively predict discussion quality, while Building on Ideas can negatively predict quality, and reveal productive sequential patterns where affective contributions are linked to evidence-based reasoning. The findings advance theory and practice by informing scaffolds and dashboards that help teachers surface and leverage interactional patterns to support deeper, more integrative ethical discussions in pluralistic learning environments.

Abstract

Engaging learners in dialogue around controversial issues is essential for examining diverse values and perspectives in pluralistic societies. While prior research has identified productive discussion moves mainly in STEM-oriented contexts, less is known about what constitutes productive discussion in ethical and value-laden discussions. This study investigates productive discussion in AI ethics dilemmas using a dialogue-centric learning analytics approach. We analyze small-group discussions among undergraduate students through a hybrid method that integrates expert-informed coding with data-driven topic modeling. This process identifies 14 discussion moves across five categories, including Elaborating Ideas, Position Taking, Reasoning & Justifications, Emotional Expression, and Discussion Management. We then examine how these moves relate to discussion quality and analyze sequential interaction patterns using Ordered Network Analysis. Results indicate that emotive and experiential arguments and explicit acknowledgment of ambiguity are strong positive predictors of discussion quality, whereas building on ideas is negatively associated. Ordered Network Analysis further reveals that productive discussions are characterized by interactional patterns that connect emotional expressions to evidence-based reasoning. These findings suggest that productive ethical discussion is grounded not only in reasoning and justification but also in the constructive integration of emotional expression.

Figures (2)

• Figure 1: Alignment between discovered discussion move clusters and SEDA labels
• Figure 2: Ordered network of discussion moves in different discussion quality