MeetMap: Real-Time Collaborative Dialogue Mapping with LLMs in Online Meetings

2025-02-03

AI Summary

Contemporary video conferencing platforms rely on linear recording, which fails to capture nonlinear, emergent conceptual associations inherent in spoken dialogue—thereby impeding participants’ comprehension and integration of meeting knowledge. To address this, we propose MeetMap: a real-time, LLM-powered visualization system that dynamically maps utterances onto a structured node-edge dialogue graph. MeetMap introduces a novel human-AI collaborative dual-mode framework: AI-Map enables low-effort, automated graph construction, while Human-Map supports user-driven semantic restructuring, aligning with human conversational mental models. The system further enables interactive exploration and synchronous collaborative editing. In a controlled user study, MeetMap significantly improved note usability (+42%) and cross-participant cognitive alignment (+38%) over conventional note-taking methods, empirically validating both the effectiveness and cognitive plausibility of dialogue mapping in live meeting contexts.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Humans and AI: Intelligent User Interfaces
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: Humans versus LLMs for data annotation and labeling
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Video meeting platforms display conversations linearly through transcripts or summaries. However, ideas during a meeting do not emerge linearly. We leverage LLMs to create dialogue maps in real time to help people visually structure and connect ideas. Balancing the need to reduce the cognitive load on users during the conversation while giving them sufficient control when using AI, we explore two system variants that encompass different levels of AI assistance. In Human-Map, AI generates summaries of conversations as nodes, and users create dialogue maps with the nodes. In AI-Map, AI produces dialogue maps where users can make edits. We ran a within-subject experiment with ten pairs of users, comparing the two MeetMap variants and a baseline. Users preferred MeetMap over traditional methods for taking notes, which aligned better with their mental models of conversations. Users liked the ease of use for AI-Map due to the low effort demands and appreciated the hands-on opportunity in Human-Map for sense-making.

Problem

• Non-linear Ideas Capturing
• Video Conferencing Platforms
• Conceptual Connection

Innovation

• Real-time Dialogue Mapping
• Large Language Models
• AI-assisted Video Meetings