Walking through Discussions: A Mobile Visual Analytics System for In-Situ Group Discussion Analysis

2026-08-09

AI Summary

This work addresses the challenge teachers face in simultaneously monitoring multiple small-group discussions and providing timely interventions in physical classrooms. To this end, we propose MobileGroupVis—the first in-situ visual analytics system designed specifically for small touchscreen devices to support real-time analysis of classroom group discussions. By integrating lightweight streaming audio analysis with conversational modeling, the system extracts structured features such as interaction patterns, topic evolution, and discussion deviations. It employs six coordinated views to seamlessly bridge multi-group overviews, in-depth single-group diagnostics, and intervention workflows. Our design innovates through compact visual encodings and tightly coupled views that balance spatial constraints of small screens with both effective overview and traceable diagnostic capabilities. Case studies and expert interviews demonstrate that MobileGroupVis effectively enables instructors to understand discussion dynamics in real time, identify anomalous groups, and deliver precise interventions.

Abstract

Group discussion-based teaching is widely used to foster collaborative learning, yet teachers in physical classrooms often struggle to simultaneously monitor multiple groups and quickly diagnose a target group before intervening. Existing visual analytics tools primarily support post-hoc analysis on desktop, providing limited support for in-situ walk-around teaching. To address this gap, we present MobileGroupVis, a mobile visual analytics system for in-situ analysis of classroom group discussions. MobileGroupVis integrates multi-group monitoring, single-group diagnosis, and instructional intervention into a concise analytical workflow tailored for small-screen touch interaction. The system is powered by a lightweight streaming analysis pipeline that converts group audio into structured discussion data and further extracts interaction patterns, topic progression, and topic deviation through a dialogue analysis module. To enable both glanceable overview and traceable diagnosis, we design six coordinated views, including a compact glyph that visually encodes word count, interaction intensity, and topic deviation for efficient cross-group comparison and anomaly localization, along with detailed views for opinion evolution, interaction dynamics, topic coverage, and dialogue records. We evaluate MobileGroupVis through two case studies and expert interviews. The results provide preliminary evidence that MobileGroupVis supports teachers in understanding discussion processes, identifying groups in need of attention, and facilitating in-class intervention.

Problem

• group discussion
• in-situ analysis
• classroom monitoring
• visual analytics
• teacher intervention

Innovation

• mobile visual analytics
• in-situ analysis
• group discussion monitoring
• streaming dialogue analysis
• coordinated views