What Makes an Initial Reaction Ready for Discussion?: Multi-Persona AI Support for Stance Reflection and Writing
2026-08-24 • Human-Computer Interaction
Human-Computer Interaction
AI summaryⓘ
The authors studied how people prepare their opinions before joining a discussion. They created StanceLab, a tool that uses three different personas—an Interviewer, Mentor, and Opponent—to help users think through their stance from multiple angles. In a small pilot test, they found that having personas identify blind spots and objections is important, and that users need help managing responses from all personas. The authors suggest improving the tool to better guide users from reflecting on different viewpoints to crafting clear, audience-aware messages.
stance preparationpersona rolesLLM modeblind spotsaudience awarenessmessage revisionpilot studyreflectionsocial issue communicationmulti-perspective feedback
Authors
Sky Shih-Kai Hong, Mu-Tien Kuo, Wei-Ji Chen
Abstract
An initial reaction to a social or community issue can feel meaningful before it is ready to become a message: people still need to clarify the claim, anticipate audience risks, and decide how much reasoning should become visible to others. We present StanceLab, a prototype for preparing a stance before entering a discussion. The prototype compares a three-persona mode, where an Interviewer, Mentor, and Opponent respond in parallel to help users diagnose and revise a stance, with a standalone LLM mode. In a formative within-subject pilot with six participants and 12 task sessions, every session produced a short final message in the notepad. The pilot revealed two design requirements: persona roles should diagnose useful blind spots or objections, and parallel responses need coordination support. We propose a future diagnosis-and-writing workflow that turns persona-based reflection into selective, audience-aware final messages.