Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Multigenre AI-powered Story Composition

Edirlei Soares de Lima, Margot M. E. Neggers, Antonio L. Furtado

TL;DR

The paper addresses preserving thematic consistency in interactive narrative generation by guiding story composition with genre-based patterns. It introduces a two-phase approach to construct these patterns—retrieving genre-consistent exemplars and applying most-specific-generalization—implemented via the PatternTeller AI agent. Grounded in Frye and Ryan's theories and incorporating five fundamental genres (comedy, romance, tragedy, satire, mystery), the authors validate their framework by generating five storyboard-style narratives from a neutral premise. The work offers a practical, controllable method for genre-guided storytelling and outlines avenues for enhancing pattern fidelity and visual consistency through future work, including a character asset library and broader experimentation.

Abstract

This paper shows how to construct genre patterns, whose purpose is to guide interactive story composition in a way that enforces thematic consistency. To start the discussion we argue, based on previous seminal works, for the existence of five fundamental genres, namely comedy, romance - in the sense of epic plots, flourishing since the twelfth century -, tragedy, satire, and mystery. To construct the patterns, a simple two-phase process is employed: first retrieving examples that match our genre characterizations, and then applying a form of most specific generalization to the groups of examples in order to find their commonalities. In both phases, AI agents are instrumental, with our PatternTeller prototype being called to operate the story composition process, offering the opportunity to generate stories from a given premise of the user, to be developed under the guidance of the chosen pattern and trying to accommodate the user's suggestions along the composition stages.

Multigenre AI-powered Story Composition

TL;DR

The paper addresses preserving thematic consistency in interactive narrative generation by guiding story composition with genre-based patterns. It introduces a two-phase approach to construct these patterns—retrieving genre-consistent exemplars and applying most-specific-generalization—implemented via the PatternTeller AI agent. Grounded in Frye and Ryan's theories and incorporating five fundamental genres (comedy, romance, tragedy, satire, mystery), the authors validate their framework by generating five storyboard-style narratives from a neutral premise. The work offers a practical, controllable method for genre-guided storytelling and outlines avenues for enhancing pattern fidelity and visual consistency through future work, including a character asset library and broader experimentation.

Abstract

This paper shows how to construct genre patterns, whose purpose is to guide interactive story composition in a way that enforces thematic consistency. To start the discussion we argue, based on previous seminal works, for the existence of five fundamental genres, namely comedy, romance - in the sense of epic plots, flourishing since the twelfth century -, tragedy, satire, and mystery. To construct the patterns, a simple two-phase process is employed: first retrieving examples that match our genre characterizations, and then applying a form of most specific generalization to the groups of examples in order to find their commonalities. In both phases, AI agents are instrumental, with our PatternTeller prototype being called to operate the story composition process, offering the opportunity to generate stories from a given premise of the user, to be developed under the guidance of the chosen pattern and trying to accommodate the user's suggestions along the composition stages.
Paper Structure (10 sections, 2 figures, 1 table)

This paper contains 10 sections, 2 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Creation of Genre Patterns
  4. Genre Characterization
  5. Characterizing by Examples
  6. Constructing the Genre Patterns
  7. Story Composition with Genre Patterns
  8. Concluding Remarks
  9. Hero’s Journey Pattern Derived from the Monomyth
  10. IMDB’s Genre Classification

Figures (2)

  • Figure 1: The user interface of PatternTeller being used to extract the pattern for the mystery genre (Pattern \ref{['pat5']}) using the following stories as input: "Murder on the Orient Express" by Agatha Christie (1934), "The Da Vinci Code" by Dan Brown (2003), and "Sherlock Holmes" series by Sir Arthur Conan Doyle (1887-1927).
  • Figure 2: The first events generated for the story "Merlin's Heiress: The Tragic Symphony of Eira's Ascension" in the storyboard style of PatternTeller.