This article is from the archive of our partner .
The New York Times is beginning to roll out an experimental new approach to personalized news that the Poynter Institute compares to Pandora's approach to suggesting music based on what users say they like. The paper is trying to provide a more social news experience that includes not only personalization but also a reader reputation system and new approach to commenting. So far, most of the new additions have been happening behind the scenes--rethinking how to do recommendations and tweaking algorithms. When the toolbar for TimesPeople, a simple social network launched in 2008, disappeared this week, Poynter's Jeff Sonderman suspected something biggest was in store and reached out to chief technology officer Marc Frons who explained some upcoming features.
Active Personalization. Six months ago, The Times launched a personalized recommendation feature that Frons says "really [exceeded] expectations in terms of usage and clickthroughs." Fron says that boost that success with new features that are differ from the typical Amazon approach of recommending items that are similar to other items you've seen. "What is new about what we’ve done is how it figures out what to give you next based on what you’ve read," Fron told Poynter. "Our algorithm tries to figure out complementary or even disparate matches that will help expose you to what we think are things you would be interested in, rather than just topics.”