A Review Selection Approach for Accurate Feature Rating Estimation

In this paper, we propose a review selection approach towards accurate estimation of feature ratings for services on participatory websites where users write textual reviews for these services. Our approach selects reviews that comprehensively talk about a feature of a service by using information distance of the reviews on the feature. The rating estimation of the feature for these selected reviews using machine learning techniques provides more accurate results than that for other reviews. The average of these estimated feature ratings also better represents an accurate overall rating for the feature of the service, which provides useful feedback for other users to choose their satisfactory services.