| K-最邻近算法在文本自动分类中的应用 |
| |
| 引用本文： | 刘卓.K-最邻近算法在文本自动分类中的应用[J].苏州市职业大学学报,2010,21(2):58-60. |
| |
| 作者姓名： | 刘卓 |
| |
| 作者单位： | 苏州科技学院,电子与信息工程学院,江苏,苏州,215011 |
| |
| 摘 要： | 对文本的自动分类进行了研究，介绍文本分类的基本过程和文本特征选取的方法，重点介绍了一种常用的基于内容的分类算法——K-最邻近算法．利用K-最邻近算法（KNN）并结合改进的词特征权值计算方法和文本相似度的计算方法完成了文本的自动分类．通过KNN方法分类之后的结果的查准率、查全率得以明显提高．
|
| 关 键 词： | 数据挖掘 文本自动分类 K－最邻近算法 |
Application of KNN Algorithm in Automatic Text Categorization |
| |
| LIU Zhuo.Application of KNN Algorithm in Automatic Text Categorization[J].Journal of Suzhou Vocational University,2010,21(2):58-60. |
| |
| Authors: | LIU Zhuo |
| |
| Institution: | LIU Zhuo (Department of Electronic Information Engineering, Suzhou University of Science and Technology, Suzhou 215011, China) |
| |
| Abstract: | Automatic classification of text is studied. The paper introduces the basic process of text classification and text feature selection method, focusing on a common content-based classification algorithm K-nearest neighbor algorithm. Text classification is completed by using K-nearest neighbor algorithm and the right combination of features to improve the value of words and text similarity calculation method.The precision rate and recall rate of results are significantly increased after using the methed of dessification by KNN. |
| |
| Keywords: | data mining text automatic classification of text K-nearest neighbor algorithm |
| 本文献已被 维普 万方数据 等数据库收录！ |
