Word sense disambiguation for spam filtering

摘要

Spam has become a major issue in computer security because it is a channel for threats such as computer viruses, worms, and phishing. More than 86% of received e-mails are spam. Historical approaches to combating these messages, including simple techniques such as sender blacklisting or the use of e-mail signatures, are no longer completely reliable. Many current solutions feature machine-learning algorithms trained using statistical representations of the terms that most commonly appear in such e-mails. However, these methods are merely syntactic and are unable to account for the underlying semantics of terms within messages. In this paper, we explore the use of semantics in spam filtering by introducing a pre-processing step of Word Sense Disambiguation (WSD). Based upon this disambiguated representation, we apply several well-known machine-learning models and show that the proposed method can detect the internal semantics of spam messages.