Finding a new book to read isn’t always easy. People on Twitter are always asking for recommendations and it is a great place to get them. Now there’s a little help at hand courtesy of this online project from the team at Knight Lab, the news media innovation group, called BookRx.
BookRx scans your Tweets and on the basis of a number of key words it recommends books for you to read in a number of categories from fiction, business, sport and science fiction.
Developed by a team of students at Northwestern University, where Knight Lab is based, the service isn’t an app but rather a content recommendation engine that simply takes a look at your Tweets in terms of the words, Twitter handles, and hashtags you use. It then looks within those categories to find books to recommend.
Maybe it is the current number of users, but the BookRx is amazingly quick. It took only a few seconds in my case to analyse my Tweets and make recommendations.
Looking at the books it recommended me two things were noticeable. There was a definite high degree of accuracy in that it suggested books that I already owned, including ones by Thomas Pynchon and a favourite author of mine in Cormac McCarthy. It also suggested others that I’ve had on my list, but never got around to buying or reading such as Nicholas Carr’s ‘The Shallows: What the Internet Is Doing to Our Brains’.
The surprise was in the titles that I’d not heard of and would never have come across, but which were definitely in the right ballpark and so encourages you to browse. When it comes to books browsing is one of the biggest joys of actual bookstores and it is also the kind of recommendation that is often missing from online bookshops, or so I’ve found.
The team behind BookRx are planning to apply the Twitter recommendation engine idea to other media, think film, TV and music. They also have plans to refine the tool so that it goes deeper. At the moment BookRx recommends best sellers, but that’s something they’d like to change.
“We’d like to evaluate for real, on a large scale; that’ll help us tune it and make it incrementally better. Also right now just because of sheer numbers it tends to recommend current best-sellers. We’d like to bias it a bit away from that at least some of the time so that you get a more diverse set of recommendations.
“And of course it would be neat to hook it directly to some booksellers so you could easily get something that caught your interest,” BookRx told HuffPo.