A comprehensive survey of research based on extraction of opinion words and opinion targets from customer reviews

Abstract

This survey paper categorizes, compares, and summarizes the algorithms, data sets and performance measurement in the published articles related to extraction of opinion targets and words from customer reviews. The systems reviewed either deploy a supervised or completely unsupervised algorithm for the process. Most of the systems rely on K-nearest neighbor algorithm or a bootstrapping approach. Most of the methods have produced a list comprising of opinion targets from the customer reviews of a product. As a result, opinion targets usually are product features or attributes. The approaches mentioned in the papers reviewed suffer either from error propagation or from lack of automation for parsing long span relations. Certain approaches have taken an initial bag of seed words and proceeded to exploit the syntactical relationship between opinion words and targets. Mainly online product reviews have been used. It is generally believed that the co- occurrence of certain target and opinion words in close proximity makes them more relevant to each other and to the product as well. Owing to the nature of online review data sets most literature have not include assessment of opinion targets and words across multiple domains.