A Novel Framework for Product Aspect Ranking Through Opinion Mining

Abstract

Numerous consumer reviews of a products are now available on the Internet. Consumer reviews contain rich and valuable knowledge for the both firms and users. However, the reviews are the often a disorganized, leading to difficulties in information navigation and knowledge acquisition. The paper proposes a product aspect ranking with opinion mining framework which automatically identifies the important aspects of products from online consumer reviews, aiming at improving the usability of the numerous reviews. The important product aspects are the identified based on two observations: The important aspects are usually commented on by a large number of consumers and consumer opinions on the important aspects greatly influence of their overall opinions on the product. Given the consumer reviews of a product, we first identify the product aspects by a shallow dependency parser and determine a consumer opinions on these aspects via a sentiment classifier. We develop a probabilistic aspect ranking algorithm to infer the importance of aspects by a simultaneously considering aspect frequency and the influence of consumer opinions given to each aspect over their overall opinions.