The importance of canonical product attributes on user opinions: An empirical investigation

Abstract

When making purchasing decisions, customers usually rely on information from two types of sources: product specifications, provided by manufacturers, and reviews, posted by other customers. Both kinds of information are often available on e-commerce websites. While researchers have demonstrated the importance of product specifications and reviews as separate and valuable sources to support purchase decision-making, a largely uninvestigated issue is what is the relationship between these two kinds of information. In this paper we present an empirical study on the use of direct and indirect mentions to canonical product attributes, that is, those defined by manufactures in product specifications, in the reviews written by customers. For this study, we analyzed more than 1,100,000 opinionated sentences available in about 650,000 user reviews from Amazon.com across five product categories. Our results indicate that user opinions are indeed guided by the attributes from product specifications and highlight the influence of canonical attributes on the user reviews.