Presentation | 2012-02-28 A Text Categorization Method by using SVM that Utilizes Evaluation Values based on the Bayes Classification as the Document Features Yutaro FUJII, Takuya YOSHIMURA, Takayuki ITO, |
---|---|
PDF Download Page | PDF download Page Link |
Abstract(in Japanese) | (See Japanese page) |
Abstract(in English) | In this paper, we propose the method of text categorization that we can get high F value with short time by using the evaluation value of the Bayes classification as features of a document required of SVM. Many bulletin board systems and social network services have become popular collaboration tools in recent years. In such system, some information, such as adult content, is not appropriate for all users, notably children. Based on the above motivation and background, we have been focusing on filtering harmful text information(especially, adult contents). Generally, in the field of document classification with SVM, people use the word frequencies as features of documents in SVM. However, in there method, F value is not so high and there is also much computation time. In the method we proposed, we can get high F value with short time by using the evaluation value of the Paul Graham system and Gray Robinson system as features of a document required of SVM. In comparative experiments with the existing method, our method result is the best in other method. |
Keyword(in Japanese) | (See Japanese page) |
Keyword(in English) | SVM / Natural Language Processing |
Paper # | AI2011-42 |
Date of Issue |
Conference Information | |
Committee | AI |
---|---|
Conference Date | 2012/2/21(1days) |
Place (in Japanese) | (See Japanese page) |
Place (in English) | |
Topics (in Japanese) | (See Japanese page) |
Topics (in English) | |
Chair | |
Vice Chair | |
Secretary | |
Assistant |
Paper Information | |
Registration To | Artificial Intelligence and Knowledge-Based Processing (AI) |
---|---|
Language | JPN |
Title (in Japanese) | (See Japanese page) |
Sub Title (in Japanese) | (See Japanese page) |
Title (in English) | A Text Categorization Method by using SVM that Utilizes Evaluation Values based on the Bayes Classification as the Document Features |
Sub Title (in English) | |
Keyword(1) | SVM |
Keyword(2) | Natural Language Processing |
1st Author's Name | Yutaro FUJII |
1st Author's Affiliation | Nagoya Institute of Technology() |
2nd Author's Name | Takuya YOSHIMURA |
2nd Author's Affiliation | Nagoya Institute of Technology |
3rd Author's Name | Takayuki ITO |
3rd Author's Affiliation | Nagoya Institute of Technology |
Date | 2012-02-28 |
Paper # | AI2011-42 |
Volume (vol) | vol.111 |
Number (no) | 447 |
Page | pp.pp.- |
#Pages | 6 |
Date of Issue |