Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Narrative Information Theory

Lion Schulz, Miguel Patrício, Daan Odijk

TL;DR

An information-theoretic framework to measure narratives is proposed, providing a formalism to understand pivotal moments, cliffhangers, and plot twists and offers creatives and AI researchers tools to analyse and benchmark human- and AI-created stories.

Abstract

We propose an information-theoretic framework to measure narratives, providing a formalism to understand pivotal moments, cliffhangers, and plot twists. This approach offers creatives and AI researchers tools to analyse and benchmark human- and AI-created stories. We illustrate our method in TV shows, showing its ability to quantify narrative complexity and emotional dynamics across genres. We discuss applications in media and in human-in-the-loop generative AI storytelling.

Narrative Information Theory

TL;DR

An information-theoretic framework to measure narratives is proposed, providing a formalism to understand pivotal moments, cliffhangers, and plot twists and offers creatives and AI researchers tools to analyse and benchmark human- and AI-created stories.

Abstract

We propose an information-theoretic framework to measure narratives, providing a formalism to understand pivotal moments, cliffhangers, and plot twists. This approach offers creatives and AI researchers tools to analyse and benchmark human- and AI-created stories. We illustrate our method in TV shows, showing its ability to quantify narrative complexity and emotional dynamics across genres. We discuss applications in media and in human-in-the-loop generative AI storytelling.

Paper Structure

This paper contains 9 sections, 5 equations, 3 figures.

Table of Contents

  1. Introduction
  2. Framework and Results
  3. States, complexity and pivots
  4. Prediction-focussed metrics: suspense and plot twists
  5. Discussion
  6. Appendix / supplemental material
  7. Dataset
  8. Analysis pipeline
  9. Choice of divergence measure

Figures (3)

  • Figure 1: Overview -- information-theoretic measures of narratives.
  • Figure 2: Results -- emotions, as well as the complexity and pivot metrics in an example episode (crime thriller) and across different shows (see appendix for details).
  • Figure 3: Supplementary figure: KL-Divergences for example show and trajectories (left) and summary statistics (right). Note the overlapping qualitative patterns with JS-D.