Tech Report

A Comparative Study of Term Weighting Methods for Information Filtering

The users of an information filtering system can only be expected to provide a small amount of information to initialize their user profile. Therefore, term weighting methods for information filtering have somewhat different requirements to those for information retrieval and text categorization. We present a comparative evaluation of term weighting methods, including one novel method, relative document frequency, designed specifically for information filtering. The best weighting methods appear to be those which balance exploiting user input and data from the collection.

ID: kmi-03-04

Date: 2003

Author(s): Nikolaos Nanas, Victoria Uren, Anne De Roeck

Resources:
Download PDF

View By

Other Publications

Latest Seminar
Microsoft Research Cambridge

Actions and their Consequences: Implicit Interactions with Machine Learned Knowledge Bases

More Details

CONTACT US

Knowledge Media Institute
The Open University
Walton Hall
Milton Keynes
MK7 6AA
United Kingdom

Tel: +44 (0)1908 653800

Fax: +44 (0)1908 653169

Email: KMi Support

COMMENT

If you have any comments, suggestions or general feedback regarding our website, please email us at the address below.

Email: KMi Development Team