A hybrid user model in text categorisation


Kim, S., Hall, W. and Keane, A.J. (2000) A hybrid user model in text categorisation In Proceedings of KDD-2000: Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Association for Computing Machinery., pp. 103-104.

Download

[img] PDF kim_00.pdf - Accepted Manuscript
Download (520kB)

Description/Abstract

A user model that specifies user preferences on message handling is an essential component of an email message categorizer. We present an approach that combines two learning algortihms, i.e. the Naive Bayesian Classifier (NBC) and Progol, to model implicitly and explicitly reflected user preferences that may not be modelled by using either the algorithms alone. An experiment demonstrates the improvement of categorization performance compared to that of using the two algorithms independently.

Item Type: Conference or Workshop Item (Paper)
Venue - Dates: KDD-2000: Sixth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2000-08-20 - 2000-08-23
Related URLs:
Keywords: Text categorization, user modelling, symbolic learning, statistical learning, email communication
Subjects: Q Science > QA Mathematics > QA75 Electronic computers. Computer science
ePrint ID: 21404
Date :
Date Event
2000Published
Date Deposited: 27 Feb 2007
Last Modified: 22 Feb 2017 00:03
Further Information:Google Scholar
URI: http://eprints.soton.ac.uk/id/eprint/21404

Actions (login required)

View Item View Item