Stacking classifiers for anti-spam filtering of e-mail

TL;DR

This paper demonstrates that stacking classifiers enhances the effectiveness of anti-spam email filtering, showing practical improvements in real-world applications using a public dataset.

Contribution

It empirically evaluates the use of stacked generalization for cost-sensitive anti-spam filtering, a novel application in text categorization.

Findings

Stacking improves anti-spam filter efficiency

Filters can be effectively used in real-life scenarios

Empirical results on a public corpus support the approach

Abstract

We evaluate empirically a scheme for combining classifiers, known as stacked generalization, in the context of anti-spam filtering, a novel cost-sensitive application of text categorization. Unsolicited commercial e-mail, or "spam", floods mailboxes, causing frustration, wasting bandwidth, and exposing minors to unsuitable content. Using a public corpus, we show that stacking can improve the efficiency of automatically induced anti-spam filters, and that such filters can be used in real-life applications.