Earticle

초록

영어

E-mail classification is an effective method to manage, improve process efficiency and filter junk mail. The extraction of E-mail characteristic is the key problem of exactness classification. In order to make the classification has a more distinct division characteristic words, IDF (Inverse document frequency) is used to epurate further the characteristic. The procedure which users deal with E-mail is a natural half-supervised learning. By using this process, proposed algorithm corrects classification results, adjust classification rule to adapt the individuation requirement of user automatically. The evaluation experiments indicate the availability of proposed algorithm.

목차

Abstract
 1. Introduction
 2. Outline of the Method
  2.1 Information Processing of E-mail head
  2.2 Subject and Body Processing of E-mail
  2.3 Classification Rules
  2.4 Classification Processing
 3. Classification Experiments
  3.1 Classification Experiments
  3.2 Evaluation of Experimental Results
  3.3 Discussion
 4. Conclusion
 Acknowledgements
 References

키워드

저자

• Zhongjian Wang [ Harbin University of Commerce, Harbin 150028, China ]
• Zongjie Wang [ Open Fund of Smart Education and Information Engineering Harbin Normal University, Harbin, 150025, China ]
• Yanfeng Gao [ Harbin University of Commerce, Harbin 150028, China ]
• Yanfen Lin [ Harbin University of Commerce, Harbin 150028, China ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of u- and e- Service, Science and Technology

• 간기

  격월간

• pISSN

  2005-4246

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605