On Narrative Information and the Distillation of Stories

TL;DR

This paper introduces the concept of narrative information and demonstrates how neural networks and evolutionary algorithms can extract and reorder media to induce storytelling, with a focus on music albums.

Contribution

It presents a novel framework combining contrastive learning and evolutionary algorithms to distill and utilize narrative templates in media.

Findings

Narrative templates are statistically present in existing music albums.

Neural networks can effectively extract narrative information from media.

The method can automatically reorder albums to induce stories.

Abstract

The act of telling stories is a fundamental part of what it means to be human. This work introduces the concept of narrative information, which we define to be the overlap in information space between a story and the items that compose the story. Using contrastive learning methods, we show how modern artificial neural networks can be leveraged to distill stories and extract a representation of the narrative information. We then demonstrate how evolutionary algorithms can leverage this to extract a set of narrative templates and how these templates -- in tandem with a novel curve-fitting algorithm we introduce -- can reorder music albums to automatically induce stories in them. In the process of doing so, we give strong statistical evidence that these narrative information templates are present in existing albums. While we experiment only with music albums here, the premises of our work extend to any form of (largely) independent media.