Some Fitting of Naive Bayesian Spam Filtering for Japanese Environment

  • Manabu Iwanaga
  • Toshihiro Tabata
  • Kouichi Sakurai
Conference paper

DOI: 10.1007/978-3-540-31815-6_12

Part of the Lecture Notes in Computer Science book series (LNCS, volume 3325)
Cite this paper as:
Iwanaga M., Tabata T., Sakurai K. (2005) Some Fitting of Naive Bayesian Spam Filtering for Japanese Environment. In: Lim C.H., Yung M. (eds) Information Security Applications. WISA 2004. Lecture Notes in Computer Science, vol 3325. Springer, Berlin, Heidelberg

Abstract

Bayesian filtering is one of the most famous anti-spam measures. However, there is no standard implementation for treatment of Japanese emails by Bayesian filtering. In this paper, we compare several conceivable ways to treat Japanese emails about tokenizing and corpus separation. In addition, we give experimental results and some knowledge obtained by the experiments.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2005

Authors and Affiliations

  • Manabu Iwanaga
    • 1
  • Toshihiro Tabata
    • 2
  • Kouichi Sakurai
    • 2
  1. 1.Graduate School of Information Science and Electrical EngineeringKyushu UniversityJapan
  2. 2.Faculty of Information Science and Electrical EngineeringKyushu UniversityJapan

Personalised recommendations