Research of E-mail Classification Based on Supervised Learning Method
Zhongjian Wang · Advanced science and technology letters · 2014
For a large number of E-mails, the classification is an effective management method. In the process of improving process efficiency and filtering junk mail, the extraction of E-mail characteristic is the key problem of exactness classification. In order to make the classification has a more distinct division characteristic words, Inverse document frequency is used. The extracted characteristic words are used to classifying mails, and the classification results are judged correct or erroneous by users. By classifying and feedback process E-mail classification rules are automatic generated and adjusted to adapt the users. The experiment results indicate the method is availability.