Method for filtering Chinese junk mail based on Logistic regression

Abstract

The invention discloses a filtering method of recursive Chinese junk E-mail, which is based on Logistic. The method comprises the following steps: first, analyzing E-mails, extracting E-mail titles, E-mail main bodies and accessory relative information, second, segmenting words for version information which is extracted, third, accounting word frequencies of entries in E-mails, calculating weights of words through utilizing TF-IDF pattern, presenting the E-mail to be characteristic vector which is weighted, fourth, utilizing an LIBLINEAR tool kit to exercise the sample of the E-mail to get an Logistic recursive module, fifth, utilizing the Logistic recursive module to classify for new E-mails, getting the probability value whether the E-mails which are got are junk E-mails. The utility which utilizes the Logistic recursive module has the advantages of simple module, little amount of parameter, and high classifying accuracy in a data set whose text number and characteristic number are both bigger, the accuracy and efficiency of filtering junk E-mails are improved through dimension reduction and improved characteristic value calculating method, and meanwhile, the problem of choosing module exercise parameter which is faced in filtering junk E-mails is effectively solved.

Description

technical field [0001] The invention relates to a junk mail filtering method, in particular to a Logistic regression-based Chinese junk mail filtering method. Background technique [0002] With the proliferation of spam, various spam filtering technologies emerged as the times require. Currently, content-based intelligent mail filtering methods have become the mainstream technology, among which support vector machine (SVM), dynamic Markov modeling (DMM), Winnow and other machine learning methods have been successfully applied to the field of mail classification. The basic idea of ​​these methods is to treat spam filtering as a two-category problem, to search for classifiers from sample mails, and to use classifiers to predict unknown mails. [0003] Generally, machine learning techniques can be divided into discriminative models (Discriminative Model, such as Logistic regression, SVM) and generative models (Generative Model, such as Bayes) two types. Practice has proved ...

AI Technical Summary

Problems solved by technology

The spam filtering technology adopted in the above patents does no...

Images