A Bayesian Classification Approach Using Class-Specific Features for Text Categorization

被引:87
作者
Tang, Bo [1 ]
He, Haibo [1 ]
Baggenstoss, Paul M. [2 ]
Kay, Steven [1 ]
机构
[1] Univ Rhode Isl, Dept Elect Comp & Biomed Engn, Kingston, RI 02881 USA
[2] Frauhnhofer FKIE, Fraunhoferstr 20, D-53343 Wachtberg, Germany
基金
美国国家科学基金会;
关键词
Feature selection; text categorization; class-specific features; PDF projection and estimation; naive Bayes; dimension reduction; SELECTION;
D O I
10.1109/TKDE.2016.2522427
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In this paper, we present a Bayesian classification approach for automatic text categorization using class-specific features. Unlike conventional text categorization approaches, our proposed method selects a specific feature subset for each class. To apply these class-specific features for classification, we follow Baggenstoss's PDF Projection Theorem (PPT) to reconstruct the PDFs in raw data space from the class-specific PDFs in low-dimensional feature subspace, and build a Bayesian classification rule. One noticeable significance of our approach is that most feature selection criteria, such as Information Gain (IG) and Maximum Discrimination (MD), can be easily incorporated into our approach. We evaluate our method's classification performance on several real-world benchmarks, compared with the state-of-the-art feature selection approaches. The superior results demonstrate the effectiveness of the proposed approach and further indicate its wide potential applications in data mining.
引用
收藏
页码:1602 / 1606
页数:5
相关论文
共 25 条
[21]   ENN: Extended Nearest Neighbor Method for Pattern Recognition [J].
Tang, Bo ;
He, Haibo .
IEEE COMPUTATIONAL INTELLIGENCE MAGAZINE, 2015, 10 (03) :52-60
[22]   A Parametric Classification Rule Based on the Exponentially Embedded Family [J].
Tang, Bo ;
He, Haibo ;
Ding, Quan ;
Kay, Steven .
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS, 2015, 26 (02) :367-377
[23]  
Wang L., 2006, Data mining with computational intelligence
[24]   A general wrapper approach to selection of class-dependent features [J].
Wang, Lipo ;
Zhou, Nina ;
Chu, Feng .
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (07) :1267-1278
[25]  
Xiuju Fu, 2002, Proceedings of the 2002 Congress on Evolutionary Computation. CEC'02 (Cat. No.02TH8600), P1890, DOI 10.1109/CEC.2002.1004531