Feature extraction and opinion classification using class sequential rule on customer product review

Abstract

Product review in e-commerce can help prospective buyers to make decision whether the product that they want to buy is good or bad and it can help the sellers to get their consumers feedback. But, there are two problems exist: the number of product review increases day by day and e-commerce allows their consumers to write positive negative opinion about some product features in one review, as known as “free format”. Therefore, there should be system which can extract product feature from review and classify their opinion automatically. Class Sequential Rule (CSR) method can be implemented in product feature extraction and Opinion Lexicon method can be implemented in feature opinion classification. The best F-score of feature extraction using CSR in free format review is 51.26% and the best f-score of opinion classification using Opinion Lexicon in free format review is 35.65%.