| 文本分类中特征项权重算法的改进 |
| |
| 引用本文： | 卢志翔,蒙丽莉.文本分类中特征项权重算法的改进[J].柳州师专学报,2011,26(4):128-131. |
| |
| 作者姓名： | 卢志翔 蒙丽莉 |
| |
| 作者单位： | 1. 广西大学计算机与电子信息学院,广西南宁,530001
2. 柳州师范高等专科学校,广西柳州,545004 |
| |
| 摘 要： | TFID作为文本特征权重计算常用方法,其不足之处是忽略了特征词在文本中的分布情况和文本长度。修正特征词后的改进TFIDF算法召回率和准确率都优于改进前TFIDF。
|
| 关 键 词： | 文本分类 特征项 权重计算 改进方法 |
On Improvement of Feature Weight Algorithm in Hierarchical Text Classification |
| |
| LU ZhiXiang,;MENG LiLi.On Improvement of Feature Weight Algorithm in Hierarchical Text Classification[J].Journal of Liuzhou Teachers College,2011,26(4):128-131. |
| |
| Authors: | LU ZhiXiang ;MENG LiLi |
| |
| Institution: | 1.School of Computer and Electronic Information,Guangxi University,Nanning,Guangxi 530001; 2.Department of Physics and Information Science,Liuzhou Teachers College,Liuzhou,Guangxi,545004 China) |
| |
| Abstract: | TFIDF（Term Frequency Inverse Documentation Frequency） is the main method of calculating the feature weight in text classification research,which ignores the distribution of feature words in text and the length of the text.To solve the problem,this paper p |
| |
| Keywords: | text classification feature item calculating the feature weight improve method |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
