Using Machine Learning to Map Fictional Worlds

Mapping Fictional Worlds is a project to create maps and virtual spaces from literary texts. This seems to be a machine learning project: using natural language processing to build a world around a text that didn’t necessarily come with a map. One component, highlighted by the Guardian, is LitCraft: creating literary worlds using Minecraft. Such as Treasure Island. More at the project’s Chronotopic Cartographies blog. [David Garcia]

Author: Jonathan Crowe

Jonathan Crowe blogs about maps at The Map Room. His nonfiction has been published by AE, The New York Review of Science Fiction, the Ottawa Citizen and Tor.com. His sf fanzine, Ecdysis, was a two-time Aurora Award finalist.