You might remember the crazy story behind CanGoogleHearMe.com: Aaron Stanton had a great idea he couldn't bring to life and he decided to pitch it to Google. Last year, he created a site to share his story and managed to convince Google to hear his idea. Since then, a lot of things have happened, other companies became interested in his project and he created a prototype, with a small team of developers.
After more than a year, the idea has been finally unveiled: "a system for matching users to books based on a full-text analysis of writing style". The system analyzes a book to determine some characteristics: pacing, density, action, description, dialog and finds similar books by comparing these characteristics. These values can be calculated for each scene from the book and they generate a graph that briefly characterizes the book.
Do you like Stephen King's It, but thought it was too long? The technology behind BookLamp allows you to find books that are written with a similar tone, tense, perspective, action level, description level, and dialog level, while at the same time allowing you to specify details like... half the length. It's impervious to outside influences - like advertising - that impact socially driven recommendation systems, and isn't reliant on a large user base to work.
The video below includes more details about this idea and its potential uses:
You can go to BookLamp.org to create an account and see the prototype, which only has information for a small number of science-fiction books. Whether Google will use this in Book Search or Amazon will use it to improve its book recommendation system, that's still an open question.
No comments:
Post a Comment