Wed Apr 5, 12:00, WeH 1327


	       "NewsWeeder: Learning to Filter Netnews"

			       Ken Lang

A significant problem in many information filtering systems
is the dependence on the user for the creation and maintenance
of a user profile, which describes the user's interests.  
NewsWeeder is a netnews-filtering system that addresses this 
problem by allowing the user to rate each article being 
read from one to five, through a Mosaic-based interface. The system 
then learns a user profile based on these ratings.  This talk 
will cover how NewsWeeder accomplishes this task, and examines
the alternative learning methods used.  Results will be presented
comparing a successful technique from Information Retrieval,
term-frequency/inverse-document-frequency (tf-idf) weighting, with
a technique based on the Minimum Description Length principle (MDL).