One month after launching its new recommendation system, Digg is already reporting positive results. Digg recommends stories based on other members with similar voting patterns and interests. Chief scientist Anton Kast writes on the Digg Blog:
- Digging activity is up significantly: the total number of Diggs increased 40% after launch.
- The Recommendation Engine is running strong: at any given point in time, the system is generating over 54 Million Recommendations, with the average Digger having nearly 200 Recommendations from an average of 34 “Diggers like you”.
- Friend activity/friends added is up 24%.
- Commenting is up 11% since launch.
Digg’s recommendation engine takes a Last.fm approach to finding people’s whose tastes overlap with yours and then suggesting stories they’ve Dugg up but that you’ve missed. It is collaborative filtering for news.
As Digg becomes more mainstream, it needs technologies such as this to bring it back to its glory days when everybody was interested in the same niche categories. Social recommendations work best when they are extracted from niche communities who are obsessive about one or two topics. Digg started out as a haven for hardcore techies, but has branched out.
The recommendation system is designed to, in effect, help Diggers carve out their own niche communities again. If you happen to like tech industry news, you will see stories from other like-minded Diggers. If you prefer politics or sports, you’ll get those stories. And if you like a combination, the system will grab recommendations from each appropriate bucket.
At least, that is how it is supposed to work in theory. The recommendations seem decent. But I personally haven’t noticed anything that really strikes home. Over time, it should get better.