Traffic Report on Q&A Sites

Hitwise published a report on traffic to Q&A sites, which has apparently gone up 889% (!) over the past two years.

Basically, Yahoo! Answers dominates U.S. traffic, getting 74% of all hits categorized as Q&A. I wonder how closely correlated traffic volume is with the volume of contributions (questions asked, and answers provided).

The report also shares some demographics, which is nice. Slight bias towards women, slightly older population (mode 30s and 40s). As I’ve argued before, I think Q&A sites are overlooked by technologists and researchers because of this demographic.

Max

More reading:

• A similar report from 16 months ago
• The WikiAnswers blog and Mashable point to this report as evidence of the rise of WikiAnswers.com.

Q&A Still Overlooked

For some reason, Q&A sites are mostly overlooked by analysts and journalists. One recent exception was an article from Slate, comparing Yahoo! Answers (unfavorably) with Wikipedia. A good read, if you’re interested in Q&A, social search, or mass collaboration web sites.

This morning, though, while catching up on my Technology Review RSS feed, I saw some analysis of Microsoft’s move to acquire Yahoo! A quoted analyst observes that this acquisition isn’t just about search, but also about Yahoo’s social properties, some of which are best in class. The interesting fact is that the two properties cited are Flickr and del.icio.us. Yes, important sites. I use both of them. What about Yahoo! Answers? Check this out:

Yahoo! Answers gets about as much traffic as Flickr, and about an order of magnitude more traffic than delicious. Also, note that while Flickr is a leader in the field (although Photobucket, Smugmug, Google’s Picasa, and Kodak’s offerings are strong competitors), Yahoo! Answers blows the rest of the Q&A field away in terms of activity. There is no other Q&A site in the US that comes close.

So, the search engine corporations know about the importance of Q&A sites. But the press and technology analysts still do not, apparently. (Nor do most researchers…that’s a different story)

I will speculate that the reason for ignoring Q&A sites to date has to do with the demographics of their users. While Flickr and Delicious are founded on relatively tech-saavy, relatively geeky users (i.e. the same demographic as technology writers), Q&A sites are often frequented by high-schoolers, stay-at-home moms, and other demographics that are typically ignored by the technology press.

What do you think? What are other reasons for ignoring Q&A sites?

Max

Activity-Balanced Clustering at RecSys 2007

Shilad, Dan, and I wrote a short paper called “Supporting Social Recommendations with Activity-Balanced Clustering“.  I presented the paper at Recommender Systems 2007 here in Minneapolis.  The idea is that standard clustering algorithms such as k-means simply don’t work well if you’re trying to create groups of users that manifest similar levels of activity.  In MovieLens, k-means placed 84% of the active users in a single cluster.  Thus, we mashed up some techniques from the clustering literature to create an algorithm that improved on k-means in terms of cluster quality and computational complexity, while giving us the balanced properties we sought.  One of the key insights is that stable matching algorithms are a clever way to evenly divide sets of things based on similarity metrics.

I received lots of feedback from conference attendees.  One of the most interesting questions (that I have not investigated) is whether there are some unique properties of the users that I clustered that led to the severe lack of balance with k-means.  I don’t think so – the 20,000 or so MovieLens users that we used as our data have two characteristics that seem particularly regular:

• Power law activity
• Normal distribution of ratings (1-5 scale)

Another person suggested that I simply didn’t tweak k-means well enough (and the other algorithms I tried).  Well, I turned plenty of knobs, many times.  In the process of the knob turning, I realized that clustering metrics are a fairly bad way of gauging the “feel” of a cluster of users.  I’d like to dig more into clustering metrics that reflect the different ways that groups of people might come together.

Max

Summer 2007 At Nokia Research

I recently returned from a very interesting summer at Nokia Research Center, Palo Alto. This lab is very young – it launched late last year – which created an atmosphere of exploration, and perhaps uncertainty. As an intern, this was a fun opportunity, as the lab culture (and especially my mentor, Joe McCarthy) encouraged original thinking and novel system building.

The project that I worked on is well summarized by Joe on his blog. It was a very fun project: lots of coding and lots of playfulness.

Some pictures: http://www.flickr.com/photos/maxharp3r/tags/nokia/

Max