@inproceedings{e7e1da2803434e70a878d98a41f2883f,
title = "GS-orthogonalization based {"}basis feature{"} selection from word co-occurrence matrix",
abstract = "Feature selection plays an important role in machinelearning applications. Especially for text data, the highdimensionaland sparse characteristics will affect the performanceof feature selction. In this paper, an unsupervised feature selection algorithm through Random Projection and Gram-Schmidt Orthogonalization (RP-GSO) from the word co-occurrence matrix is proposed. The RP-GSO has three advantages: (1) it takes as input dense word co-occurrence matrix, avoiding the sparseness of original document-term matrix, (2) it selects {"}basis features{"} by Gram-Schmidt process, guaranteeing the orthogonalization of feature space, and (3) it adopts random projection to speed upGS process. We did extensive experiments on two real-world textcorpora, and observed that RP-GSO achieves better performancecomparing against supervised and unsupervised methods in textclassification and clustering tasks.",
keywords = "Basis feature, GS-Orthogonalization, Random projection",
author = "Deqing Wang and Hui Zhang and Rui Liu",
note = "Publisher Copyright: {\textcopyright} 2015 IEEE.; 15th IEEE International Conference on Data Mining, ICDM 2015 ; Conference date: 14-11-2015 Through 17-11-2015",
year = "2016",
month = jan,
day = "5",
doi = "10.1109/ICDM.2015.80",
language = "英语",
series = "Proceedings - IEEE International Conference on Data Mining, ICDM",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1027--1032",
editor = "Charu Aggarwal and Zhi-Hua Zhou and Alexander Tuzhilin and Hui Xiong and Xindong Wu",
booktitle = "Proceedings - 15th IEEE International Conference on Data Mining, ICDM 2015",
address = "美国",
}