Michael Pazzani gave a course on Web personalization at UC Irvine this winter, and has made allsome of his slides available online. Topics covered include user profiling and collaborative filtering. Recommender systems such as Amazon and TiVo are examined. There’s a link to an interesting paper by Ali and van Stam describing the TiVo collaborative filtering system.
I just stumbled across a project called StumbleUpon whose primary goal seems to be to offer collaborative filtering of the Web, using the same "thumbs up" and "thumbs down" iconography as TiVo does.
They've also got elements of a social network and personals/matchmaking component included, but the primary idea is to be brought to websites semi-randomly which you rate yay/nay and it continues to suggest new sites based on your ratings and the ratings of others who rated similarly to you (ala Amazon's "other people also bought").
1. Dossy on March 17, 2005 12:36 PM writes...
I just stumbled across a project called StumbleUpon whose primary goal seems to be to offer collaborative filtering of the Web, using the same "thumbs up" and "thumbs down" iconography as TiVo does.
They've also got elements of a social network and personals/matchmaking component included, but the primary idea is to be brought to websites semi-randomly which you rate yay/nay and it continues to suggest new sites based on your ratings and the ratings of others who rated similarly to you (ala Amazon's "other people also bought").
Permalink to Comment