Myanmar Spam Filtering based on Naïve Bayesian Learning Algorithm (MSFNBLA)

Spam is one of the main problems in e-mailscommunication. Naïve Bayesian (NB) learning isuseful algorithm for constructing Myanmarspam corpus (SCorpus) from pre-defined spamand ham e-mails. SCorpus is built on theassumption that the characteristics of e-mails inthe training dataset. Content-based analysis isparticularly effective in filtering spam. NB playsa critical role in probabilistic learning andcalculates the probability of an e-mail beingspam based on its contents. The motivation forthis paper is to find a solution for the Internetusers in Myanmar e-mails received every day intheir mailboxes. There is no standardimplementation for treatment of Myanmar emails.So, a classification filter for the e-mailsshould be proposed with SCorpus. NB approachis being popular for learning corpus. To filter thespam e-mail, paper MSFNBLA is applied forclassifying the incoming e-mail is spam or ham