AI-Assisted Sensemaking

Human-in-the-loop tooling to surface insights across conversations [Archived]

Research

Sensemaking often demands significant human effort to identify themes, summarize insights, and share findings with community partners. This ongoing project explores how AI can support and streamline the process—reducing time and labor while preserving quality and human agency. By integrating AI, researchers aim to enhance consistency across sensemakers, offer training support, and facilitate the sharing of best practices. The goal is to design a human-led, AI-assisted approach that makes qualitative analysis more accessible and scalable.

Sensemaking, Generative AI
Read the Abstract

Home     >     Research     >     AI-Assisted Sensemaking

Collaborators

Thanh Mai Phan

Research Software Engineer

Jad Kabbara

Research Affiliate (IBM Research)

Maya Detwiller

Prototype Manager

Marina Rakhilin

Program Lead

Dennis Jen

Lead Software Engineer

Professor Dimitra Dimitrakopoulou

Principal Research Scientist, Head of Translational and Practice

Published Abstract

Jad Kabbara, Thanh-Mai Phan, Marina Rakhilin, Maya E Detwiller, Dimitra Dimitrakopoulou, and Deb Roy. 2025. AI-assisted sensemaking: Human-AI collaboration for the analysis and interpretation of recorded facilitated conversations. In Proceedings of the Extended Abstracts of the CHI Conference on Human Factors in Computing Systems (CHI EA ’25). Association for Computing Machinery, New York, NY, USA, Article 655, 1–8. https://doi.org/10.1145/3706599.3706688

More Research

All Research

New Social Forms

Exploring new rituals, formats, and structures for coming together

Pilots & Programs

Communication, Listening, Design, Playful Interaction, Workplace Communication

Storyline

An auditable AI framework for tracing competing narratives across podcasts, conversations, and news

Research

Computational Social Science, Large Language Model, Communication, Sensemaking, Responsible AI, Narrative

AI-Assisted Conversation Highlighting

Discovering semantically or emotionally salient moments in spoken discourse using LLMs

Research

Sensemaking, Generative AI, Human-Computer Interaction

realtalk@Boston

A new civic infrastructure in Boston grounded in dialogue as a way to building “civic muscle” of democracy

Pilots & Programs

Research, Sensemaking, Conversation Facilitation, Participatory Research, Listening

Anthology

An AI interface that turns raw conversation audio into interactive maps

Research

Communication, Conversation Visualization, Sensemaking, Data Visualization, Civic Engagement

Agora

A training ground to practice consensus-finding with real human perspectives

Research

Computational Social Science, Bridging, Data Visualization, Civic Engagement, Deliberation, Conflict Resolution