E-mail messages are originally designed to be sent and accumulated in repository for periodical use which amounts to the details of an event or a meeting’s upcoming agenda for a particular organization. These messages range from static organizational knowledge to conversations and pose a lot of difficulties to users in terms of prioritizing and processing of the contents of both stored and new incoming messages. This research has established a classification model which classifies the accumulated e-mails in the mail inbox known as dataset into four classes: critical, urgent, important and others. Electronic mail extractor application was designed and implanted to extract e-mail contents. The application used heuristic technique based on Term Frequency- Inverse Document Frequency (TF-IDF) to determine what keywords in a dataset of e-mail messages might be more favorable to use in a query. Nuclass 7.1 Artificial Neural Network (ANN) software was used in the implementation of automated e-mail classification into userdefined word classes corresponding to preformatted class identity, and was able to learn in an associative learning approach, in which the network was trained by providing it with input and matching output patterns. This study showed that Neural Networks (NN) using Back Propagation (BP) technique combined with electronic mail extractor can be successfully used for automated e-mail classification into meaningful classes.

Electronic mail massively known as e-mail has been a competent and widely accepted communication mechanism as the Internet community increases. This has necessitated attention towards managing and maintaining e-mail because it is prone to misuse both at individual and organizational levels (Taiwo et al., 2010). The major challenges that are most supreme in e-mail management are disordered e-mail messages, and congested and unstructured e-mails in mail boxes. It may be very hard to find stored e-mail messages, search for previous e-mails with specified contents or features when the mails are not well-structured and organized (Androutsopoulos et al., 2000).

E-mail messages are originally designed to be sent, accumulated in repository and periodically collected and read by recipient, which amounts to the details of an event or a meeting’s upcoming agenda for a particular organization. Schuff et al. (2007) have studied e-mail to be widely used to synchronize real-time communication which does not conform with its primary goal. The need for effective management of e-mails arose since most people rely on e-mails for efficiency and effectiveness of communication as mailboxes may become congested. Messages range from static organization knowledge to conversations with such a wide possibility of messages. Users may find it difficult to prioritize and successfully process the contents of new incoming messages. Also, it may be difficult to find a previously stored message in the mailbox (Schuff et al., 2007).

Electronic mail is of different types and categories depending on the users’ interest. Some important electronic mails such as confirmation of bank account or any account, delivery or meeting notification are always received with good mind without any complaint since they are expected e-mails. Away from this, there are some unscrupulous and unanticipated e-mails from different sources such as newsletters, event planning, marketing, error messages from broken Universal Resource Locator (URL), virus e-mails and spam e-mails (Saldana, 2009).

Other categories include: transactional alerts, marketing, duplicates, opt-in confirmations, welcome messages, opt-out confirmations, apologies and corrections to the broken URL in the preceding e-mail, add notifications, inscrutable blank messages, spam and viruses (Mock et al., 1997).

Information Technology Journal, Electronic mail extractor, Term Frequency-Inverse Document Frequency (TFIDF),
Artificial Neural Network (ANN), Back Propagation (BP), E-mail classification.