Human-AI Narrative Synthesis to Foster Shared Understanding in Civic Decision-Making

2025-09-23

AI Summary

In representative political contexts such as school districts, voluminous community feedback overwhelms conventional aggregation methods, impeding shared understanding between civic leaders and constituents. To address this, we propose StoryBuilder—a human-in-the-loop narrative synthesis framework that pioneers experience-centered automated narrative generation, transforming structured feedback into first-person narratives. Integrated with the mobile-first StorySharer platform, it facilitates public dialogue. Our approach combines natural language processing, composite narrative modeling, and mixed-methods research design to enable end-to-end translation from large-scale opinions to interpretable, empathetic narratives. Field deployment yielded 124 synthesized narratives; empirical evaluation demonstrated that lived-experience-based narratives significantly enhance intergroup respect (*p* < 0.01) and institutional trust (*p* < 0.05), revealing critical mechanisms through which narrative structure shapes public cognition and attitudes.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Natural Language Processing: Ethics — Bias, Fairness, Transparency & Privacy
• Application Domains: Humanities & Computational Social Science

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Trust and reliance of crowd workers and data experts on GenAI

Abstract

Community engagement processes in representative political contexts, like school districts, generate massive volumes of feedback that overwhelm traditional synthesis methods, creating barriers to shared understanding not only between civic leaders and constituents but also among community members. To address these barriers, we developed StoryBuilder, a human-AI collaborative pipeline that transforms community input into accessible first-person narratives. Using 2,480 community responses from an ongoing school rezoning process, we generated 124 composite stories and deployed them through a mobile-friendly StorySharer interface. Our mixed-methods evaluation combined a four-month field deployment, user studies with 21 community members, and a controlled experiment examining how narrative composition affects participant reactions. Field results demonstrate that narratives helped community members relate across diverse perspectives. In the experiment, experience-grounded narratives generated greater respect and trust than opinion-heavy narratives. We contribute a human-AI narrative synthesis system and insights on its varied acceptance and effectiveness in a real-world civic context.

Problem

• Overwhelming volumes of community feedback overwhelm traditional synthesis methods
• Barriers to shared understanding between civic leaders and community members exist
• Massive community input creates challenges for fostering cross-perspective understanding

Innovation

• Human-AI collaborative pipeline for narrative synthesis
• Generated composite stories from community feedback
• Deployed narratives through mobile-friendly StorySharer interface