- Title
- A new supervised term ranking method for text categorization
- Creator
- Mammadov, Musa; Yearwood, John; Zhao, Lei
- Date
- 2010
- Type
- Text; Conference paper
- Identifier
- http://researchonline.federation.edu.au/vital/access/HandleResolver/1959.17/34892
- Identifier
- vital:3836
- Identifier
- ISBN:0302-9743 (ISSN)
- Abstract
- In text categorization, different supervised term weighting methods have been applied to improve classification performance by weighting terms with respect to different categories, for example, Information Gain, χ2 statistic, and Odds Ratio. From the literature there are three term ranking methods to summarize term weights of different categories for multi-class text categorization. They are Summation, Average, and Maximum methods. In this paper we present a new term ranking method to summarize term weights, i.e. Maximum Gap. Using two different methods of information gain and χ2 statistic, we setup controlled experiments for different term ranking methods. Reuter-21578 text corpus is used as the dataset. Two popular classification algorithms SVM and Boostexter are adopted to evaluate the performance of different term ranking methods. Experimental results show that the new term ranking method performs better. © 2010 Springer-Verlag.
- Publisher
- Adelaide, SA
- Relation
- Paper presented at 23rd Australasian Joint Conference on Artificial Intelligence, AI 2010 Vol. 6464 LNAI, p. 102-111
- Rights
- Open Access
- Rights
- This metadata is freely available under a CCO license
- Subject
- Classification algorithm; Classification performance; Controlled experiment; Data sets; Information gain; Multi-class; Odds ratios; Ranking methods; Term weight; Term weighting; Text categorization; Text corpora; Three-term; Artificial intelligence; Text processing
- Full Text
- Reviewed
- Hits: 4367
- Visitors: 4498
- Downloads: 338
Thumbnail | File | Description | Size | Format | |||
---|---|---|---|---|---|---|---|
View Details Download | SOURCE1 | Submitted version | 215 KB | Adobe Acrobat PDF | View Details Download |