Text Classification for Spam Filtering Using Naive Bayes

An efficient anti-spam filter that would block all spam, without blocking any legitimate messages is a growing need. To address this problem, we examine the effectiveness of statistically-based approaches Naïve Bayesian anti-spam filters, as it is content-based and self-learning (adaptive) in nature. Additionally, we designed a derivative filter based on relative numbers of tokens. We train the filters using a large corpus of legitimate messages and spam and we test the filter using new incoming personal messages. More specifically, four filtering techniques available for a Naïve Bayesian filter are evaluated. We look at the effectiveness of the technique, and we evaluate different threshold values in order to find an optimal anti-spam filter configuration. Based on cost-sensitive measures, we conclude that additional safety precautions are needed for a Bayesian anti-spam filter to be put into practice. However, our technique can make a positive contribution as a first pass filter.