DocumentCode :
1802155
Title :
Chinese sentiment classification based on semantic structure of sentences
Author :
Yang, Yushu ; ZHOU, Yanquan
Author_Institution :
Res. Center of Intell. of Sci. & Technol., Beijing Univ. of Posts & Telecommun., Beijing, China
Volume :
3
fYear :
2011
fDate :
24-26 Dec. 2011
Firstpage :
1745
Lastpage :
1749
Abstract :
Chinese unique expression has a significant impact on sentiment classification. According to the different semantic structures, we adopt two views, direct and indirect views. Here, direct views consist of those sentences which directly express speaker´s feeling and preference towards a target object while indirect views focus on statements towards a target object for evaluation and then indirectly express speaker´s Orientation. Experimental results demonstrate the effectiveness of our proposed approach.
Keywords :
natural language processing; pattern classification; text analysis; Chinese sentiment classification; Chinese unique expression; direct view; semantic structure; sentence; speaker feeling; Entropy; Pragmatics; Direct View; Domain-independent; Indirect View; Maximum Entropy; Semantic Structure; Sentiment Classification;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computer Science and Network Technology (ICCSNT), 2011 International Conference on
Conference_Location :
Harbin
Print_ISBN :
978-1-4577-1586-0
Type :
conf
DOI :
10.1109/ICCSNT.2011.6182306
Filename :
6182306
Link To Document :
بازگشت