All Things Email

About | Contact

Filtron: A Learning-Based Anti-Spam Filter

by Eirinaios Michelakis, Ion Androutsopoulos, Georgios Paliouras, George Sakkis, Panagiotis Stamatopoulos

Conference on Email and Anti-Spam, 2004-07-30
Language: English

Note: Published at CEAS 2004.

External links

Full text: PDF

Information about this paper

Abstract

Abstract. We present Filtron, a prototype anti-spam lter that integrates the main empirical con- clusions of our comprehensive analysis on using machine learning to construct e ective personalized anti-spam lters. Filtron is based on the experimental results over several design parameters on four publicly available benchmark corpora. After describing Filtron's architecture, we assess its behavior in real use over a period of seven months. The results are deemed satisfactory, though they can be improved with more elaborate preprocessing and regular re-training.

Creative Commons. Some Rights Reserved.
Copyright © 2004 Jochen Topf
Unless otherwise noted the contents on this site are licensed under the
Creative Commons Attribution-ShareAlike License.