| 基于贝叶斯公式的自适应垃圾邮件过滤方法 |
| |
| 引用本文： | 宁绍军,邹恒明. 基于贝叶斯公式的自适应垃圾邮件过滤方法[J]. 计算机应用与软件, 2007, 24(11): 189-191 |
| |
| 作者姓名： | 宁绍军 邹恒明 |
| |
| 作者单位： | 上海交通大学软件学院,上海,200240;上海交通大学计算机科学与工程系,上海,200030 |
| |
| 摘 要： | 简单贝叶斯算法在邮件过滤领域使用得比较普遍.该算法的优点是简单、对特征较为恒定的垃圾邮件较为有效,但其适应性较差.谨提出一种以贝叶斯公式为基础的自适应垃圾邮件过滤方法,它采用基于词熵的特征提取方法,在过滤过程中不断地进行自学习,具有较强的自适应能力.
|
| 关 键 词： | 垃圾邮件过滤 文本分类 贝叶斯算法 自学习 |
| 修稿时间： | 2005-09-13 |
SELF-ADAPTABLE SPAM FILTERING BASED ON BAYESIAN ALGORITHM |
| |
| Ning Shaojun,Zou Hengming. SELF-ADAPTABLE SPAM FILTERING BASED ON BAYESIAN ALGORITHM[J]. Computer Applications and Software, 2007, 24(11): 189-191 |
| |
| Authors: | Ning Shaojun Zou Hengming |
| |
| Affiliation: | 1. School of Software, Shanghai Jiaotong University, Shanghai 200240, China; 2. Department of Computer Science and Engineering, Shanghai Jiaotong University, Shanghai 200030 |
| |
| Abstract: | Naive Bayesian algorithm has widely been applied to spam filtering for its simpleness.But when the attributes of spams change,effectiveness of this algorithm falls greatly.A self-adaptable spam filtering method based on bayesian algorithm is presented,which adopts a way of attribute selection based on word entropy and has ability of continuous learning. |
| |
| Keywords: | Spam filitering Text classifier Bayesian algorithm Continuous learning |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
