Proxona: Supporting Creators' Sensemaking and Ideation with LLM-Powered Audience Personas

2024-08-20

AI Summary

Existing tools struggle to extract deep audience insights from user comments or deliver actionable feedback. This paper introduces the first LLM-driven, interactive audience profiling system designed specifically for content creators, establishing a “creator–audience co-creation” framework. Grounded in real user comments, it employs feature distillation, multidimensional clustering, and persona instantiation to generate dialogue-capable, multidimensional audience personas, supporting simulated feedback and iterative narrative refinement. Technical evaluation confirms the diversity and representativeness of the generated personas; empirical studies with 11 creators demonstrate the system’s efficacy in uncovering latent audience segments, generating early-stage content insights, and significantly enhancing confidence in narrative strategy decisions. The core innovations are data-grounded, dynamic persona modeling and an interactive ideation mechanism.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Cognitive Modeling & Cognitive Systems: Computational Creativity
• Natural Language Processing: Generation

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

A content creator's success depends on understanding their audience, but existing tools fail to provide in-depth insights and actionable feedback necessary for effectively targeting their audience. We present Proxona, an LLM-powered system that transforms static audience comments into interactive, multi-dimensional personas, allowing creators to engage with them to gain insights, gather simulated feedback, and refine content. Proxona distills audience traits from comments, into dimensions (categories) and values (attributes), then clusters them into interactive personas representing audience segments. Technical evaluations show that Proxona generates diverse dimensions and values, enabling the creation of personas that sufficiently reflect the audience and support data grounded conversation. User evaluation with 11 creators confirmed that Proxona helped creators discover hidden audiences, gain persona-informed insights on early-stage content, and allowed them to confidently employ strategies when iteratively creating storylines. Proxona introduces a novel creator-audience interaction framework and fosters a persona-driven, co-creative process.

Problem

• Enhancing content creators' audience understanding
• Generating interactive, multi-dimensional audience personas
• Supporting iterative content refinement with simulated feedback

Innovation

• LLM-powered audience personas
• Interactive multi-dimensional personas
• Persona-driven co-creative process