Voting-based classification for e-mail spam detection

The problem of spam e-mail has gained a tremendous amount of attention. although entities tend to use e-mail spam filter applications to filter out received spam e-mails,marketing companies still tend to send unsolicited e-mails in bulk and users still receive a reasonable amount of spam e-mail despite those filtering applications. this work proposes a new method for classifying e-mails into spam and non-spam. first,several e-mail content features are extracted and then those features are used for classifying each e-mail individually. the classification results of three different classifiers (i.e. decision trees,random forests and k-nearest neighbor) are combined in various voting schemes (i.e. majority vote,average probability,product of probabilities,minimum probability and maximum probability) for making the final decision. to validate our method,two different spam e-mail collections were used. © 2016 published by itb journal publisher.