BookLamp is launching a new kind of book recommendation engine today that scans the texts of its partner publishers to establish what it calls "Book DNA."
Much like Pandora assigns specific qualities to music, BookLamp measures the story components of a book (characteristics like history, domestic environments, physical injury) and how it's written (density, pacing, dialog, description, motion).
It uses these descriptions to suggest books you might like based on a book you've liked in the past, turning up books that match the actual style and content of the text rather than books people like you have purchased in the past. The objective is an improved online browsing experience.
"I'll start off in science fiction, end up in fantasy, wander over historical fiction, wander over to some western," explains CEO Aaron Stanton. "There's this easy and smooth transition between genres and meta data that is hard to do in other systems."
Stanton and his team have been developing relationships with publishers throughout the past several years. The technology behind BookLamp has been used primarily in the publishing process. It can, for instance, help publishers refine their targeting and marketing if they can figure out who responded to similar books in the past.
Stanton intends to keep publishers as BookLamp's main customers. The motivation behind the public-facing site is partly to entice new publishers to purchase BookLamp's tools.
The libraries of Random House and Kensington Books make up the majority of the about 20,000 books currently cataloged on the site. That's a relatively limited collection. Which brings Stanton to the second current objective of BookLamp.org:
"It's up to the community [and publishers] to tell us if we're doing something worthwhile," he says. "And we hope they look at this and say, 'I like the idea, I can see what they're doing with it, but it really needs an extra 100,000 books. What do can I do to help?'"
