Invited Talk: Opinionated Product Recommendation: Mining User-Generated Reviews for Recommendation Knowledge

The web is awash with user-generated reviews, which have become increasingly important in helping shoppers choose between product and services. These reviews can provide a rich source of product recommendation knowledge since they encode the opinions and experiences of large numbers of users. Can we extract and use such features as the basis for a type of experiential product description? Do these features represent a viable alternative to more conventional product descriptions made up of meta-data or catalog features? And can these experiential product cases be used for the purpose of recommendation?

In this talk we will explore the use of opinion mining techniques to extract meaningful product descriptions from user-generated reviews and evaluate their use in a novel approach to product recommendation that combines product similarity and feature sentiment. We will describe the results of a recent evaluation using Amazon and TripAdvisor data to demonstrate the utility and generality of this approach for recommendation.