Towards a better book recommendation service

The ideal discovery platform requires not one, but many input sources

The ideal content discovery service has yet to be invented. Plenty have tried but none have truly succeeded. The latest is venture is BookScout from Random House. It’s a nifty Facebook app that uses your social graph to help you discover relevant content. As Laura Hazard Owen recently discovered though, it’s far from perfect.

Reading Laura’s post reminded me of something a wise person told me last year: Just because I’m Facebook friends with you doesn’t mean we have the same reading interests. In fact, I’d be willing to bet my reading interests don’t map very well to any of my friends, real or virtual.

That’s the problem. We try to take one aspect of our lives and have it spit out book recommendations. That model is doomed to fail every time.

I’d like to propose a completely new book recommendation model. Rather than just looking at my Facebook friends, who I follow on Twitter or any other single activity, why not roll them all together and build an algorithm around everything I do online?

Monitor my Gmail. Track every website I visit. Keep a record of the various searches I do on Google. Log all the books I look at on, Google Play and every other catalog I visit. Keep a close eye on the RSS feeds I actually read. Study the Facebook posts I comment on and every word in each of my tweets. Look at everything I clip on Findings. Use it all!

Privacy freaks are ready to explode at this point. They can’t imagine why anyone would allow themselves to be tracked this closely. Fine. They don’t have to participate. I would though, especially if it leads to better recommendations. And I bet it would.

tags: , ,