Posts Tagged ‘google reader’

Google Reader Shared Items

Posted: 16 December 2007 in Uncategorized
Tags: , , , , ,

Google Reader recently added some social networking features. You can now add your friends’ shared items to your feeds. Up til now I haven’t used the shared items feature since it didn’t really make sense to send people a link to my shared items and expect them to give a crap. Now it’s easier to subscribe to it and the decision to give a crap is left up to them when they read their feeds.

As Robert Scoble pointed out, there is one major flaw with the new feature: it clutters up the rest of your feeds. This is, of course, assuming you read your feeds in the “All feeds” folder. I usually don’t since I have a number of Tech News feeds that I’m not always interested in and often has duplicated information. I only read it when I have time. You can do the same with your friends shared items, so no big deal to me.

So why not check out my shared items?  As it happens, I have none at the moment.  But if you use Google Reader, feel free to add/invite me so we can view each others.  I’ll accept any invitations.

Since I work with recommender systems, I’d hardly be doing my job if I didn’t notice things like Google Reader’s new feed recommendations. From the description of how the recommender works on the Google help page (which is unfortunately not very specific):

Your recommendations list is automatically generated. It takes into account the feeds you’re already subscribed to, as well as information from your Web History, including your location. Aggregated across many users, this information can indicate which feeds are popular among people with similar interests. For instance, if a lot of people subscribe to feeds about both peanut butter and jelly, and you only subscribe to feeds about peanut butter, Reader will recommend that you try some jelly.

This sounds like they are using a hybrid recommender system. When you are recommending items (in this case feeds) to users, you can either consider the qualities of the items themselves (content-based) or the behavior of people similar to you (collaborative filtering). The Netflix Prize is a collaborative filtering case for the most part, though it is possible to add in some amount of content. (more…)