Skip to content
11 May 2005 / erikduval


An interesting approach to personalized search was decribed in a paper on, which apparently uses dmoz to cluster and rank clusters. One thing that struck me is that it is difficult to evaluate this sort of work through real experiments, because the results of the search engines keep changing…

Regrettably, time was very limited, and I didn’t quite get where the personalization comes from. I guess that the proceedings will need to give more details: see “A personalized search engine based on web-snippet hierarchical clustering” by P. Ferragina and Antonio Gull, Dipartimento di Informatica, Pisa.

Some surfing on the snakeT website reveals lots of other interesting stuff, including a way to compare search results from different search engines. Some of the results from that comparison web site are a bit confusing, but it certainly does include interesting alternative search sites, like teoma.

This is exactly the sort of exciting new stuff that I love to discover at a conference!

In the mean time, I have set up a technorati newsfeed for WWW2005 related blog postings. WWW2005 blogging seems pretty tame for now…


Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Google+ photo

You are commenting using your Google+ account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )


Connecting to %s

%d bloggers like this: