福州大学学报（自然科学版）2011，Vol.39Issue(2)：192-197,6.DOI:CNKI:35-1117/N.20110402.1006.018
基于非负矩阵分解的中文倾向性句子识别
Identification of Chinese opinion sentence based on NMF
摘要
Abstract
This paper proposes a new method for the identification of sentence opinion based on nonnegative matrix factorization (NMF, SNMF and WNMF). The method constructs feature matrix, then applies NMF, SNMF and WNMF to reduce dimensionality of matrix and extract the potential latent semantic information, and finally uses SVM to identify opinion sentences. The experiments shows that,compared with PCA and SYD, NMF, SNMF and WNMF can not only do better in reducing dimensionality and extracting potential latent semantic information, but also can get higher accuracy.关键词
NMF/识别/中文倾向性句子/倾向性分析Key words
NMF/ identification/ Chinese opinion sentence/ opinion mining分类
信息技术与安全科学引用本文复制引用
廖祥文,陈振伟..基于非负矩阵分解的中文倾向性句子识别[J].福州大学学报（自然科学版）,2011,39(2):192-197,6.基金项目
福建省自然科学基金资助项目(2010J05133) （2010J05133）
福建省科技创新平台资助项目(2009J1007) （2009J1007）
福州大学科技发展基金资助项目(2010-XQ-22) （2010-XQ-22）
