Skip to main navigation Skip to search Skip to main content

A novel weighting formula and feature selection for text classification based on rough set theory

  • Harbin Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Weighting formula and feature selection are key preprocessing in text classifying and mining. We analyze the drawbacks of weighting formula based on inverse document frequency and present a novel feature weighting and selecting method based on variable precision rough set model. Inverse document frequency (IDF) doesn't take the classification information into account and the criterion based on IDF is not monotonous with the contribution that a feature makes to classification, which will decrease the classifier's performance. The measure of classification quality based on variable rough set model can deal with complicate classification. It measures the contribution a feature makes to classification. It is introduced as a criterion for feature selecting and weighting in text classification. We name it as TFACQ. The experimental results show that the weighting formula and feature selection based on TFACQ have greatly improved the performance.

Original languageEnglish
Title of host publicationNLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings
EditorsChengqing Zong
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages638-645
Number of pages8
ISBN (Electronic)0780379020, 9780780379022
DOIs
StatePublished - 2003
EventInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003 - Beijing, China
Duration: 26 Oct 200329 Oct 2003

Publication series

NameNLP-KE 2003 - 2003 International Conference on Natural Language Processing and Knowledge Engineering, Proceedings

Conference

ConferenceInternational Conference on Natural Language Processing and Knowledge Engineering, NLP-KE 2003
Country/TerritoryChina
CityBeijing
Period26/10/0329/10/03

Fingerprint

Dive into the research topics of 'A novel weighting formula and feature selection for text classification based on rough set theory'. Together they form a unique fingerprint.

Cite this