DiaryPlay: AI-Assisted Authoring of Interactive Vignettes for Everyday Storytelling

2025-07-15

AI Summary

Interactive vignettes remain inaccessible to everyday storytellers due to high authoring complexity. This paper proposes an AI-augmented authoring framework for daily narrative creation: given natural-language input, a large language model (LLM) automatically extracts three core narrative elements—environment, characters, and events—and a novel LLM-based narrative planner transforms linear stories into branching “bottleneck” structures that support audience choice, while preserving authorial intent. Technically, the system achieves character behavior fidelity comparable to human-authored content. A user study confirms its efficacy in lowering authoring barriers and enabling highly engaging, immersive interactive experiences. To our knowledge, this is the first work to deeply integrate LLMs into interactive narrative planning for non-expert creators, advancing the democratization of interactive storytelling.

Technology Category

• Humans and AI: Game Design — Procedural Content Generation & Storytelling
• Planning, Routing, and Scheduling: Planning with Language Models
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

An interactive vignette is a popular and immersive visual storytelling approach that invites viewers to role-play a character and influences the narrative in an interactive environment. However, it has not been widely used by everyday storytellers yet due to authoring complexity, which conflicts with the immediacy of everyday storytelling. We introduce DiaryPlay, an AI-assisted authoring system for interactive vignette creation in everyday storytelling. It takes a natural language story as input and extracts the three core elements of an interactive vignette (environment, characters, and events), enabling authors to focus on refining these elements instead of constructing them from scratch. Then, it automatically transforms the single-branch story input into a branch-and-bottleneck structure using an LLM-powered narrative planner, which enables flexible viewer interactions while freeing the author from multi-branching. A technical evaluation (N=16) shows that DiaryPlay-generated character activities are on par with human-authored ones regarding believability. A user study (N=16) shows that DiaryPlay effectively supports authors in creating interactive vignette elements, maintains authorial intent while reacting to viewer interactions, and provides engaging viewing experiences.

Problem

• Reduces authoring complexity for interactive vignettes
• Transforms single-branch stories into multi-branch structures
• Maintains authorial intent while enabling viewer interactions

Innovation

• AI extracts core elements from natural language
• LLM transforms story into branch-and-bottleneck structure
• System maintains authorial intent during interactions