Naive Bayes Spam Filtering Using Word Position Attributes

This paper explores the use of the naive Bayes classifier as the basis for personalized spam filters. Various machine learning algorithms, including variants of naive Bayes, have previously been used for this purpose, but the author’s implementation using word position based attribute vectors gives very good results when tested on several publicly available corpora. The effect of various forms of attribute selection—removal of frequent and infrequent words, respectively, and by using Mutual Information—is investigated. It is also shown how n-grams, with n > 1, may be used to boost classification performance. Finally, a weighting scheme for cost-sensitive classification of variable length attribute vectors is introduced.