Using Topic Sentiment Sentences to Recognize Sentiment Polarity in Chinese Reviews

An approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences is presented. Considering the features of Chinese reviews, we firstly identify the topic of a review using an n-gram matching approach. To extract candidate topic sentiment sentences, we compute the semantic similarity between a given sentence and the ascertained topic and meanwhile determine whether the sentence is subjective. A certain number of these sentences are then selected as representatives according to their semantic similarity value with relation to the topic. The average value of the representative topic sentiment sentences is calculated and taken as the sentiment polarity of a review. Experiment results show that the proposed method is feasible and can achieve relatively high precision.

[1]  Chao Wang,et al.  A semantic classification approach for online product reviews , 2005, The 2005 IEEE/WIC/ACM International Conference on Web Intelligence (WI'05).

[2]  Wenying Zheng,et al.  Sentiment Classification of Chinese Traveler Reviews by Support Vector Machine Algorithm , 2009, 2009 Third International Symposium on Intelligent Information Technology Application.

[3]  Janyce Wiebe,et al.  Learning Subjective Adjectives from Corpora , 2000, AAAI/IAAI.

[4]  Ellen Riloff,et al.  Creating Subjective and Objective Sentence Classifiers from Unannotated Texts , 2005, CICLing.

[5]  Razvan C. Bunescu,et al.  Sentiment analyzer: extracting sentiments about a given topic using natural language processing techniques , 2003, Third IEEE International Conference on Data Mining.

[6]  Janyce Wiebe,et al.  Learning Subjective Language , 2004, CL.

[7]  Peter D. Turney.  Thumbs Up or Thumbs Down? Semantic Orientation Applied to Unsupervised Classification of Reviews , 2002, ACL.

[8]  Bing Liu,et al.  Mining and summarizing customer reviews , 2004, KDD.

[9]  Hong Yu,et al.  Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences , 2003, EMNLP.

[10]  Hsin-Hsi Chen,et al.  Mining opinions from the Web: Beyond relevance retrieval , 2007, J. Assoc. Inf. Sci. Technol..

[11]  Bo Pang,et al.  Thumbs up? Sentiment Classification using Machine Learning Techniques , 2002, EMNLP.

[12]  Wu Peng.  Research on the Recognition of Text Valence , 2009 .

[13]  Soo-Min Kim,et al.  Determining the Sentiment of Opinions , 2004, COLING.

[14]  Jun Zhao,et al.  Sentence Sentiment Analysis Based on Multi-redundant-labeled CRFs , 2007 .