Just before Christmas the Knight Lab launched BookRx, a project that analyzes your tweets and recommends books based on what it finds.
BookRx is similar to other projects in our Social Loupe. In the first phase, it analyzes your tweets (the words, Twitter usernames, and hashtags you use) and compares them to terms that are correlated with book categories. In the second phase, it looks within those categories to find specific books to recommend, again based on correlations with the terms in your tweets, which enables it to make a recommendation.
We’ve had generally positive feedback so far (along with the occasional complaint, of course). It’s been one of our more popular projects, with about 40,000 unique visitors from around the world and coverage from Mashable, LifeHacker, La Tribune, and Huffington Post.
The La Tribune reporter was particularly tickled to see that BookRx recommended “Why Nations Fail” to French president François Hollande. To be fair, Barack Obama receives the same recommendation, which reveals one of area where BookRx could be improved — its bias toward best sellers.
The bias is unintentional and is a result of the system collecting data on books that are discussed most on Twitter, which just happen to be best sellers. BookRx’s inventors, Ph.D student Shawn O’Banion and professor Larry Birnbaum, are working on ways to uncover less popular books.
Of course, the best way to learn about BookRx is to give it a try yourself.
We’re always looking to improve and would love your feedback. Tweet at us or leave a comment below after giving it a shot.