Personalized Recommendation System Based On Online Reviews

Recommendation system is a new technology to recommend products forcustomers from huge amounts of products, which infers those objective users’preferences based on their personal information or online behavior. As the Internet isgrowing rapidly, recommendation system has been applied to many Internetapplications, especially E-commerce. The traditional recommendation algorithms onlyrely on the overall rating or some hidden data, such as customers’ browsing behavior, toinfer customers’ interest. While as website contents keep on refining, and customersrequire continuous improvement of recommendations and services, old algorithms andtraditional data meet their shortcomings, for example, low efficiency and low accuracy.As is known to all, effective data is the key factor to ensure accuracy during data miningprocedure. So the first problem we need to solve is to find and introduce more refineduser data.To address this issue, this paper studied the main personalized recommendationtechnology for current E-commerce, then proposed a hybrid recommendation algorithmbased on opinion mining. This system combines web data mining technology, that is,takes advantage of user-generated-content by mining customers’ online reviews. It iswell known that online reviews can directly reflect customer’s real emotion andexpectation, so it’s appropriate to extract a customer’s latent interest and preferencefrom his/her reviews, thus refine recommendation and improve accuracy. This paperdesigned a personalized recommendation system framework, provided a solution forreality. Meanwhile, an experiment was conducted and the result demonstrated that oursystem could generate a reliable and realistic recommendation.