Paper: Using Topic Sentiment Sentences to Recognize Sentiment Polarity in Chinese Reviews

ACL ID W10-4119
Title Using Topic Sentiment Sentences to Recognize Sentiment Polarity in Chinese Reviews
Venue Joint Conference on Chinese Language Processing
Session Main Conference
Year 2010
Authors

An approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences is presented. Considering the features of Chinese re- views, we firstly identify the topic of a review using an n-gram matching ap- proach. To extract candidate topic senti- ment sentences, we compute the seman- tic similarity between a given sentence and the ascertained topic and meanwhile determine whether the sentence is sub- jective. A certain number of these sen- tences are then selected as representa- tives according to their semantic simi- larity 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 ...