计算机科学 ›› 2016, Vol. 43 ›› Issue (10): 225-228.doi: 10.11896/j.issn.1002-137X.2016.10.043
李军怀,付静飞,蒋文杰,费蓉,王怀军
LI Jun-huai, FU Jing-fei, JIANG Wen-jie, FEI Rong and WANG Huai-jun
摘要： 特征选择是文本分类技术中重要的处理步骤,特征词选择的优劣直接关系到后续文本分类结果的准确率。使用传统特征选择方法如互信息(MI)、信息增益(IG)、χ2统计量(CHI)等提取的特征词仍存在冗余。针对这一问题,通过结合词频-逆文档率(TF_IDF)和最大相关最小冗余标准(MRMR),提出了一种基于MRMR的特征词二次选取方法TFIDF_MRMR。实验结果表明,该方法可以较好地减少特征词之间的冗余,提高文本分类的准确率。
| [1] Yang Yi-ming,Pedersen J O.A comparative study on feature se-lection in text categorization[C]∥Proceedings of the 14th International Conference on Machine Learning(ICML).1997:412-420 [2] Wang De-qing,Zhang Hui,Liu Rui,et al.t-Test feature selection approach based on term frequency for text categorization[J].Pattern Recognition Letters,2014,45(11):1-10 [3] Harun U.A two-stage feature selection method for text categorization by using information gain,principal component analysis and genetic algorithm[J].Knowledge-Based Systems,2011,24(7):1024-1032 [4] Meng Jia-na,Lin Hong-fei,Yu Yu-hai.A two-stage feature se-lection method for text categorization[C]∥2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).IEEE,2010:1492-1496 [5] Kursat U A,Serkan G.A Novel Probabilistic Feature Selection Method For Text Classification[J].Knowledge-Based Systems,2012,36(6):226-235 [6] Kashif J,Sammen M,Babri Haroon A.A two-stage Markovblanket based feature selection algorithm for text classification[J].Neurocomputing,2015,7:91-104 [7] Lu Zhong-ning,Zhang Bao-wei.A text categorization methodbased on improved TF-IDF function[J].Journal of Henan Normal University(Natural Science Edition),2012,0(6):158-160(in Chinese) 卢中宁,张保威.一种基于改进TF-IDF函数的文本分类方法[J].河南师范大学学报(自然科学版),2012,0(6):158-160 [8] Carol F,Rindflesch T C,Milton C,et al.Natural language processing:state of the art and prospects for significant progress,a workshop sponsored by the National Library of Medicine[J].Journal of Biomedical Informatics,2013,46(5):765-773 [9] Saleh S N,El-Sonbaty Y.A feature selection algorithm with redundancy reduction for text classification[J].Computer and Information Sciences,2007,22:1-6 [10] Lin Yao-jin,Hu Qing-hua,Liu Jing-hua,et al.Multi-label fea-ture selection based on max-dependency and min-redundancy[J].Neurocomputing,2015,168:92-103 [11] Ding C,Peng Han-chuan.Minimum redundancy feature selection from microarray gene expression data[J].Journal of Bioinformatics and Computational Biology,2005,3(2):185-205 [12] George F,Guyon I,Elisseeff A.An extensive empirical study of feature selection metrics for text classification[J].Journal of Machine Learning Research,2003,3:1289-1305 [13] Feng Guo-he.Review of Performance Evaluation of Text Classification[J].Journal of Intelligence,2011,0(8):66-70(in Chinese) 奉国和.文本分类性能评价研究[J].情报杂志,2011,0(8):66-70 [14] NetEase article classification experiment data set[EB/OL].http://www.datatang.com/data/11967(in Chinese) 网易文章分类实验数据集[EB/OL].http://www.datatang.com/data/11967 |
| No related articles found! |
|
||
首页