Edward Nawotka at Publishing Perspectives reports on an interesting new site called BookLamp.org that is taking a Pandora-style approach to books. It breaks a book down into thematic elements and other variables, assigns them a percentage rating, and classifies them so that people who enjoy one book can search for other books that share similar elements.
“Say you’re looking for a novel like the The Da Vinci Code. We have found that it contains 18.6% Religion and Religious Institutions, 9.4% Police & Murder Investigation, 8.2% Art and Art Galleries, and 6.7% Secret Societies & Communities, and other elements — we’ll pull out a book with similar elements, provided it is in our database,” says [BookLamp CEO Aaron] Stanton.
The site only covers about 20,000 books right now, and is aimed at readers. However, it will soon be offering publishers the ability to upload their manuscripts and have them categorized, so that they can use the site to search for similar works and keep on top of trends.
The site is an interesting idea, though I can’t help think it works better for music, where the works are shorter so you will experience a greater variety over time. And I tend to think that for book recommendations, the collaborative filtering “if you liked…” approach used by AlexLit works a bit better. It’s less granular, but the blind nature of it is also one of its strengths—recommendations are based solely on how well people with similar tastes to yours liked the work, not on anything internal to it.
Still, it’s not a solution in search of a problem—the question of how to find good texts in the digital era becomes increasingly more urgent as more and more people self-publish. The more solutions people try, the sooner we will learn which ones actually work.