Detailed Information
Cited 0 time in 
Cited 0 time in 
Cited 0 time in
Metadata Downloads
Improving Document Classification Using Fine-Grained Weights
- Authors
- Song, Soo-Hwan; Lee, Chang-Hwan
- Issue Date
- 2015
- Publisher
- SPRINGER-VERLAG BERLIN
- Keywords
- Multinomial naive Bayes; Value weighting
- Citation
- CURRENT APPROACHES IN APPLIED ARTIFICIAL INTELLIGENCE, v.9101, pp 488 - 492
- Pages
- 5
- Indexed
- SCOPUS
- Volume
- 9101
- Start Page
- 488
- End Page
- 492
- ISSN
- 0302-9743
1611-3349
- Abstract
- In this paper document classification methods using multinomial naive Bayes are improved in a number of ways. We use the value weighting method, a new fine-grained weighting method, to calculate the weights of the feature values. Our experiments show that the proposed approach outperforms other state-of-the-art methods.
- Files in This Item
- There are no files associated with this item.
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.