Re:Getting the News — Evan Williams
by papercruncher on Tuesday February 28, 2012 @03:42PM
(#3644879)
Building a model and personalizing a news stream on a per-user basis is entirely feasible today. Even with very simple ML, you can see some very good real world results.
To avoid the problem of not being able to surface new topics because the user model has converged somewhere, you can use a bandit approach(seriously, who comes up with these names?). By that we mean that you do a bit of exploration by showing news topics drawn at random from some distribution and then adapt your model to what you learned. The naive implementation is "Every random(10,20) news items suggested by the recommender, display 1 drawn at random from the entire corpus. Adapt_Model(user_clicked)"
Re:Getting the News — Evan Williams
by joelthelion on Tuesday February 28, 2012 @11:52AM
(#3643807)
Depends how the recommenders are designed. If they are properly designed, they can remember what they have served you, and automatically inject some diversity into the mix. Actually, they could probably do it much better than current news solutions.
When recommenders are applied to news you'll get more of the stuff you like, but you're losing out because you are not seeing the stuff you didn't know that you would like.