中文摘要：

本文提出了一种个性化垃圾邮件过滤方法，它能够根据用户反馈自动学习出用户兴趣，并随时间的推移自动适应用户兴趣的变化。该方法首先抽取邮件的语言特征和行为特征构建多个基于规则的单独过滤器，然后采用SVM集成学习方法组合这些单独过滤器的结果。为了提高学习速度、减少用户提供反馈的数量，本文采用了主动学习方法挑选更加富含知识的邮件请求用户给出反馈。实验结果表明：集成学习和主动学习相结合的个性化过滤方法在个性化程度、分类准确率、过滤速度以及自动学习能力等方面具有更好的性能。

英文摘要：

This paper proposes a personal spam email filtering method, which can learn a user＇s in terests and update it automatically according to the user＇s feedback. The proposed method extracts the linguistic features and behavior ones to build some rule-based individual filters, and uses the SVM en- semble learning method to combine the multi-filter＇s results. Applying an active learning method to choose those knowledgeable emails with the user＇s labels, the method can minimize the number of la- beled emails and reach steady-state performance more quickly. The experimental results show the personal filtering method based on ensemble learning and active learning can capture personality, and achieve high performance with the considerations on accuracy, efficiency and learning ability.