| With the rapid development of B2C e-commerce and the popularity of online shopping, the Web storages huge number of product reviews comment by customers. Product reviews contain subjective feelings of customers who have used some products. These subjective texts reflect people's opinions, attitudes and positions. So information of subjective texts provides important commercial value. On one hand, product reviews can help manufacturers understand the impression and popularity of their products in the eyes of customers. This case gives research and development department important information on product improvements to enhance the competitiveness of products in the market. On the other hand, before making a purchasing decision, potential consumers often read product reviews of B2C online shopping mall to analyze quality information about products and then decide to buy or not. Product reviews can guide customers to make wise decisions effectively.In this paper, basing on text mining and opinion mining technology, we propose an opinion mining model of product reviews in Web. The new model firstly classifies opinion sentences of subjective texts into three types: context independent opinions, the first type of context dependent opinion, the second type of context dependent opinion.According to the characteristics of different types of opinion sentences, we use appropriate opinion mining technology to cope with problem of semantic polarity. Current studies of dealing with context dependent opinions are deficient. The proposed method concentrates on two type contextual dependent opinions. We use linguistic rules and contextual information extraction to infer the semantic orientations of opinions.At last, we get product reviews from Amazon online shopping mall as the linguistic resource to carry out experiment. Comparing the experiment results with"Opinion Observer"and"FBS", we find out the proposed method can infer the semantic orientations of three types of opinion sentences effectively. |
PDF Full Text Request