支持向量机及其在邮件过滤中的应用

Support Vector Machine and its Application in the E-mail Filtering

电子邮件已经成为了人们日常生活中不可缺少的通讯方式,然而垃圾邮件的泛滥给计算机网络安全带来威胁并给人们正常的信息交流带来了极大的不便,因此反垃圾邮件日益重要。支持向量机是在统计学习理论的基础上发展起来的新型机器学习算法,在解决小样本学习、非线性及高维模式识别问题中表现较好。因此采用支持向量机对垃圾邮件进行过滤,首先将文本类型的邮件进行预处理,提取合适的邮件特征,把邮件转化成向量空间模型,最后用支持向量机方法进行分类。实验表明支持向量机提高了过滤性能。

E - mail has become an indispensable way in people~ daily life. However, vast of spam has threatened the computer network security and has brought great inconvenience to people＇s normal information exchange, so anti - spam is becoming more and more important. Support vector machine which is based on statistical learning theory has been developed a new machine learning method. It can solve small - sample, non - linear and high dimension problems. Therefore, support vector machine is applied to spam filtering. At first, the e - mail is preprocessed, the appropriate features are extracted, the e - mail is transformed into a space vector. At last, support vector machine is used to classify the e - mail. Experimental results showed that support vector machine could improve the filtering performance.