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

TL;DR

DiaryPlay introduces an AI-assisted authoring system that turns natural-language everyday stories into interactive vignettes by extracting environment, character, and event elements and reformulating them into a branch-and-bottleneck narrative. The system combines an Interactive Vignette Elements Extractor for lightweight authoring with a Controlled Divergence Module that runtime-plans believable NPC behaviors while preserving the author’s intended storyline, enabling diverging player actions without full multi-branch authoring. Technical and user studies (N=16 each) show that the CD Module produces believability on par with human authors and that authors can create interactive vignettes within a lightweight timeframe, while viewers report engaging, immersive experiences. DiaryPlay thus demonstrates a practical path for integrating interactive storytelling into everyday social media, while outlining design considerations, ethical risks, and avenues for broader applicability and future work.

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.

Figures (8)

• Figure 1: User interface of the research probe, which includes: (a) a text story input box, (b) a display of the automatically generated scene featuring objects mentioned in the story and characters acting on events, and (c) a chat feature.
• Figure 2: DiaryPlay system overview. The Interactive Vignette Authoring Component takes the author's text story as input, extracts core elements (environment, characters, and events), and guides the author in refining them into structured interactive vignette elements. The Interactive Vignette Viewing Component enlivens NPCs and allows the player to control the PC, enabling an interactive narrative experience grounded in the authored storyline.
• Figure 3: Illustration of the branch-and-bottleneck structure in interactive storytelling. Solid black circles represent key events that all players encounter, ensuring alignment with the author-intended storyline. Hollow circles represent divergent events, which offer optional or personalized paths that allow for variation in viewing experience. Despite branching paths, the narrative converges at key events.
• Figure 4: Authoring interface, including (a1) Text story input, (a2) Characters panel, (a3) Events panel, and (a4) Environment panel; and Viewing interface, including (b1) Text story caption and (b2) Interactive vignette.
• Figure 5: Steps in the Authoring Scenario.