On Narrative Information and the Distillation of Stories
This work addresses the challenge of narrative extraction and reordering for media like music albums, offering a novel computational approach with potential applications in various independent media forms.
The paper tackled the problem of automatically inducing stories in media by introducing narrative information and using neural networks to distill stories, then applying evolutionary algorithms and a novel curve-fitting algorithm to reorder music albums, providing strong statistical evidence that narrative templates exist in existing albums.
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.