基于位置及词频信息的优化CHI文本特征选择 方法基于位置及词频信息的优化CHI文本特征选择 方法.pdf

Computer Science and Application 计算机科学与应用, 2015, 5(9), 322-330 Published Online September 2015 in Hans. /journal/csa /10.12677/csa.2015.59040 An Improved CHI Text Feature Selection Method Based on the Location and Word Frequency Information Aling Song, Haifeng Liu, Shousheng Liu Institute of Sciences, PLA University of Science and Technology, Nanjing Jiangsu Email: hfliu1962@ nd th st Received: Oct. 2 , 2015; accepted: Oct. 16 , 2015; published: Oct. 21 , 2015 Copyright © 2015 by authors and Hans Publishers Inc. This work is licensed under the Creative Commons Attribution International License (CC BY). /licenses/by/4.0/ Abstract Text feature selection is the core technology of text automatic categorization. Aiming at the short- comings of classical CHI model, we have screened the feature set which is based on the point of view of the positive and negative correlation between the feature and categories firstly. According to the type of deflection classification conditions, we adjust the feature weighting secondly. Third- ly, basing on characteristics of word frequency, we gradually improve the model based on the characteristics of a specific location in the text and the characteristics of distribution of informa- tion between classes. Finally, we propose an optimized CHI feature selection method. Text classi- fication experiments demonstrate the effectiveness of the optimized CHI model. Keywords Feature Selection, Chi-Square, Relevance, Location Distribution, Class Deflection 基于位置及词频信息的优化CHI文本特征选择 方法 宋阿羚，刘海峰，刘守生 解放军理工大学理学院，江苏 南京 Email: hfliu1962@ 文章引用: 宋阿羚, 刘海峰, 刘守生. 基于位置及词频信息的优化CHI 文本特征选择方法[J]. 计算机科学与应用, 2015, 5(