A work in progress! In Bookalator (https://github.com/indiamos/bookalatorJS), India Amos plays around with some Project Gutenberg texts and a popular set of natural language–processing tools.
For now, browse all the words in Jane Austen’s PERSUASION, see how many times each occurs, and view all the sentences in which a given word is used.
• Compare two books to see which words they share and which are unique to each.
• Compare the words used in sets of books.
• View some graphical representations of usage data.
• Maybe be able to upload some text and find out who in the collection appears most likely to have written it.
This project uses the natural (https://www.npmjs.com/package/natural) library, as well as natural-gutenberg (https://github.com/RichardLitt/natural-gutenberg). Future iterations will involve D3 and the beautiful Wordnik API.
Project Members: India Amos