Nanas, Nikolaos; Uren, Victoria and De Roeck, Anne
(2004).
| URL: | http://ieeexplore.ieee.org/xpls/abs_all.jsp?isnumb... |
|---|---|
| DOI (Digital Object Identifier) Link: | http://dx.doi.org/doi:10.1109/DEXA.2004.1333442 |
| Google Scholar: | Look up in Google Scholar |
Abstract
Users of information filtering systems cannot be expected to provide large amounts of information to initialize a 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 a new method, relative document frequency, designed specifically for information filtering. The best weighting methods appear to be those that favor information provided by the user, over information from a general collection.
| Item Type: | Book Chapter |
|---|---|
| Copyright Holders: | 2004 IEEE |
| ISBN: | 0-7695-2195-9, 978-0-7695-2195-4 |
| ISSN: | 1529-4188 |
| Extra Information: | This paper appears in: Proceedings of the 15th International Workshop on Database and Expert Systems Applications (DEXA’04) 30 Aug.-3 Sept. 2004 |
| Keywords: | information filtering; relevance feedback; statistical analysis; text analysis; information retrieval; term weighting methods; text categorization |
| Academic Unit/Department: | Mathematics, Computing and Technology > Computing Knowledge Media Institute Mathematics, Computing and Technology |
| Interdisciplinary Research Centre: | Centre for Research in Computing (CRC) |
| Item ID: | 18949 |
| Depositing User: | Colin Smith |
| Date Deposited: | 19 Nov 2009 11:52 |
| Last Modified: | 02 Dec 2010 20:41 |
| URI: | http://oro.open.ac.uk/id/eprint/18949 |
Actions (login may be required)
| View Item | |
| Public: Report issue / request change |