Sentiment Analysis of Chinese Sentences Based on Word Embedding and Syntax Tree

doi:10.3969/j.issn.1006-2475.2016.08.006

Abstract

Abstract: With the rapid development of Internet, the network is filled with a lot of subjective texts. How to judge the emotional polarity of these subjective statements is the key of the text sentiment analysis. In this paper, a method of sentiment analysis of Chinese sentences based on the word embedding and syntax tree structure is proposed. In view of the large number of network words, word embeddings are used to compute the semantic similarity between words, and the emotional polarity of the target word is gained. Some sentiment rules are defined for the phenomenon of emotional polarity transfer. Then, we judge the sentiment of sentences according to the syntax tree structure of the sentences. Experiments show that this method can solve the problem of the network words. Simultaneously, the precision and recall rate of the method are improved, and it also can be used widely in different domains.

Key words: sentimental lexicon, word embedding, syntax tree, sentiment analysis

CLC Number:

TP391.1

XIANG Ruo-chen, SUN Mei-feng. Sentiment Analysis of Chinese Sentences Based on Word Embedding and Syntax Tree[J]. Computer and Modernization, doi: 10.3969/j.issn.1006-2475.2016.08.006.

References

[1] Pang Bo, Lee L, Vaithyanathan S. Thumbs up? Sentiment classification using machine learning techniques[C]// Proceedings of the ACL-02 Conference on Empirical Methods in Natural Language Processing. 2002,10:79-86.

[2] 王素格,杨安娜,李德玉,等. 基于支持向量机的文本倾向性分类研究[J]. 中北大学学报(自然科学版), 2008,29(5):421-425.

[3] Ye Qiang, Zhang Ziqiong, Law R. Sentiment classification of online reviews to travel destinations by supervised machine learning approaches[J]. Expert Systems with Applications, 2009,36(3-Part 2):6527-6535.

[4] Eirinaki M, Pisal S, Singh J. Feature-based opinion mining and ranking[J]. Journal of Computer and System Sciences, 2012,78(4):1175-1184.

[5] 刘鲁,刘志明. 基于机器学习的中文微博情感分类实证研究[J]. 计算机工程与应用, 2012,48(1):1-4.

[6] 党蕾,张蕾. 一种基于知网的中文句子情感倾向判别方法[J]. 计算机应用研究, 2010,27(4):1370-1372.

[7] 吴江,唐常杰,李太勇,等. 基于语义规则的Web金融文本情感分析[J]. 计算机应用, 2014,34(2):481-485.

[8] 冯时,付永陈,阳锋,等. 基于依存句法的博文情感倾向分析研究[J]. 计算机研究与发展, 2012,49(11):2395-2406.

[9] Gao Kai, Xu Hua, Wang Jiushuo. A rule-based approach to emotion cause detection for Chinese micro-blogs[J]. Expert Systems with Applications, 2015,42(9):4517-4528.

[10] 肖红,许少华. 基于句法分析和情感词典的网络舆情倾向性分析研究[J]. 小型微型计算机系统, 2014,35(4):811-813.

[11] 王志涛,於志文,郭斌,等. 基于词典和规则集的中文微博情感分析[J]. 计算机工程与应用, 2015,51(8):218-225.

[12] 知网. HowNet[DB/OL]. http://www.keenage.com/, 2015-12-19.

[13] Rumelhart D E, Hintont G E, Williams R J. Learning representations by back-propagating errors[J]. Nature, 1986,323(6088):533-536.

[14] Mikolov T, Chen Kai, Corrado G, et al. Efficient estimation of word representations in vector space[C]// Proceedings of the 2013 International Conference on Learning Representations Workshop Track. 2013.

[15] Mikolov T, Sutskever I, Chen K, et al. Distributed representations of words and phrases and their compositionality[C]// Advances in Neural Information Processing Systems. 2013:3111-3119.

[16] 熊富林,邓怡豪,唐晓晟. Word2vec的核心架构及其应用[J]. 南京师范大学学报(工程技术版), 2015,15(1):43-48.

[17] 搜狗网. 全网新闻数据(SogouCA)[DB/OL]. http://www.sogou.com/labs/dl/ca.html, 2012-08-10.

[18] 谭松波. 中文情感挖掘语料—ChnSentiCrop[DB/OL]. http://www.nlpir.org/?action-viewnews-itemid-77, 2011-04-19.

[19] Socher R, Huval B, Manning C D, et al. Semantic compositionality through recursive matrix-vector spaces[C]// Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning. 2012:1201-1211.