| 基于SVM的以词性和依存关系为特征的句子倾向性判断分析 |
| |
| 引用本文： | 吴明芬,陈涛.基于SVM的以词性和依存关系为特征的句子倾向性判断分析[J].五邑大学学报(自然科学版),2012(4):66-71. |
| |
| 作者姓名： | 吴明芬 陈涛 |
| |
| 作者单位： | 中国科学院计算技术研究所;五邑大学计算机学院 |
| |
| 基金项目： | 中国科学院计算技术研究所智能信息处理重点实验室开放课题基金资助项目(LIP2010-5);广东省科技计划资助项目(2010B010600039);广东省自然科学基金资助项目(S2011010003681);江门市科技计划资助项目(2012003009398) |
| |
| 摘 要： | 将句法平面词的词性特征、依存关系、依存关系中的词性特征、邻接依存关系、邻接依存关系中的词性特征与倾向性词汇和倾向性搭配作为支持向量机（SVM）分类器的特征集，以句子为单位对多个领域的文本进行倾向性判断．通过交叉验证的方式，估计出分类器的精度为95．6％．据此提出句子倾向性分析可不以句子倾向性判断为前提．
|
| 关 键 词： | 倾向性判断 依存关系 词性特征 支持向量机 |
Sentences Tendency Judgement by POS and Dependency Based on SVM |
| |
| WU Ming-fen,CHEN Tao.Sentences Tendency Judgement by POS and Dependency Based on SVM[J].Journal of Wuyi University(Natural Science Edition),2012(4):66-71. |
| |
| Authors: | WU Ming-fen CHEN Tao |
| |
| Institution: | 1,2(1.Institute of Computing Technology,Chinese Academy of Sciences,Beijing 100190,China;2.School of Information Science,Wuyi University,Jiangmen 529020,China) |
| |
| Abstract: | The objective sentences of multi-domain from views is distinguished by using part of speech, dependency relationship, the part of speech combinations of the two words under one dependency, two adjacent dependencies, the part of speech combinations of the three words under two adjacent dependencies, sentiment words and sentiment collocations as features of SVM classifier. The precision is about 95.6% with 10-fold cross-validation. It is assumed that the sentence tendency judgement is not the premise of the document sentiment analysis. |
| |
| Keywords: | tendency judgement dependency part-of-speech characteristics support vector machine |
| 本文献已被 CNKI 维普 等数据库收录！ |
