| Due to the development of web2.0 and e-commerce, there is a tremendous rise of product reviews providing insights for merchants. The algorithm that processes useful information from reviews has become a research hot spot. The user Etailers want to know about the sentiment tendency of previous user Etailers likely inferring customers’ preference/tendency. Sentiment analysis algorithm is to get the tendency of the previous users’ given opinion. However, merchants barely understand why the tendency is positive. Under such circumstances, content awareness is the solution to figure out why the tendency is positive.This thesis would introduce our work on content aware in three major areas: feature,opinion,match. The feature means the words which could denote the shop,such as taste,environment,service and so on. The opinion means the words that modify the feature such good,bad,nice, sweet and so on. The match means one feature follows with one opinion,such as taste-nice,environment-good. We present a hybrid method for aspect-based content sense of Chinese restaurant reviews. Two main components are employed so as to extract feature-opinion pairs in the proposed method: domain independent language patterns found in Chinese and a lexical base built for restaurant reviews. The language patterns focus on the general knowledge which is implicit contained in Chinese, thus can be used directly by other domains without any modification. The lexical base, on the other hand, targets for particular characteristics of a given domain and acts as a plug-in part in our prototype system, thus does not affect the portability when applying the proposed approach in practice.Empirical evaluation shows that our method performs well and it can gain a progressive result when each component takes into effective. Our experiment data comes from the biggest review website. Comparing with the classic algorithm, our algorithm has got f-score 66%, precision 55%, recall 83%. The related paper has already been published. |
PDF Full Text Request