Recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences

Abstract

We present an approach to recognizing sentiment polarity in Chinese reviews based on topic sentiment sentences. 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.