Summary: | 碩士 === 國立成功大學 === 資訊管理研究所 === 103 === Nowadays, tourism has become a part of life. Before reserving hotels, customers need some information, which the most important source is online reviews, about hotels to help them make decisions. Due to the dramatic growing of online reviews, it is impossible for customers to read all reviews manually. Therefore, designing an automatic review analysis system, which summarizes reviews, is necessary. The main purpose of the system is to understand the opinion of reviews, which may be positive or negative. In other words, the system would analyze whether the customers who visited the hotel like it or not. Using sentiment analysis methods will help the system achieve the purpose. In sentiment analysis methods, the target of opinion (we call it “feature”) should be recognized to clarify the polarity of the opinion because polarity of the opinion may be ambiguous. Hence, we propose an unsupervised method using Part-Of-Speech pattern and multi-lexicons sentiment analysis to summarize all reviews and help customers know hotels as well as make decisions efficiently. Experimental results show that our method outperforms the state of the art methods with F-measure .628.
|