Feature-level sentiment analysis for Chinese product reviews

Author

Zhang, Haiping ; Yu, Zhengang ; Xu, Ming ; Shi, Yueling

Author_Institution

Dept. of Comput. Sci., Hangzhou Dianzi Univ., Hangzhou, China

Volume

2

fYear

2011

fDate

11-13 March 2011

Firstpage

135

Lastpage

140

Abstract

The sentiment analysis for English product reviews has been widely researched in recent years, followed with many important achievements. Due to the special language traits of Chinese, the study on Chinese product reviews is much more difficult than the former. In this work, we focus on the finer-grained sentiment analysis for Chinese product reviews, that is feature-level based sentiment analysis. We propose a hybrid method which combines association rules and point-wise mutual information to extract the product features, and then take advantage of the sentiment dictionary - HowNet to analyze the opinion orientation expressed on the product features. The experiment result obtained shows the effectiveness and efficiency of our approach.

Keywords

data mining; feature extraction; natural languages; retail data processing; Chinese product review; English product review; HowNet; association rules; feature level sentiment analysis; finer grained sentiment analysis; pointwise mutual information; product feature extraction; sentiment dictionary; Dictionaries; Digital cameras; Feature extraction; Filtering; Mobile handsets; Portable computers; Semantics; Chinese product reviews; feature extracting; feature-level sentiment analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer Research and Development (ICCRD), 2011 3rd International Conference on

Conference_Location

Shanghai

Print_ISBN

978-1-61284-839-6

Type

conf

DOI

10.1109/ICCRD.2011.5764099

Filename

5764099