Combining similarity and sentiment in opinion mining for product recommendation

Abstract

In the world of recommender systems, so-called content-based methods are an important approach that rely on the availability of detailed product or item descriptions to drive the recommendation process. For example, recommendations can be generated for a target user by selecting unseen products that are similar to the products that the target user has liked or purchased in the past. To do this, content-based methods must be able to compute the similarity between pairs of products (unseen products and liked products, for example) and typically this is achieved by comparing product features or other descriptive elements. The approach works well when product descriptions are readily available and when they are detailed enough to afford an effective similarity comparison. But this is not always the case. Detailed product descriptions may not be available since they can be expensive to create and maintain. In this article we consider another source of product descriptions in the form of the user-generated reviews that frequently accompany products on the web. We ask whether it is possible to mine these reviews, unstructured and noisy as they are, to produce useful product descriptions that can be used in a recommendation system. In particular we describe a novel approach to product recommendation that harnesses not only the features that can be mined from user-generated reviews but also the expressions of sentiment that are associated with these features. We present a recommendation ranking strategy that combines similarity and sentiment to suggest products that are similar but superior to a query product according to the opinion of reviewers, and we demonstrate the practical benefits of this approach across a variety of Amazon product domains.

Collaborative Recommendation System Using Dynamic Content based Filtering, Association Rule Mining and Opinion Mining

“…With the arrival of Web 2.0 now people are actively writing their experiences about various products, services and other things in the form of reviews. Reviews are now other sources of data for generating recommendations [20]. Many ecommerce websites are having large number reviews about various products written by their customers.…”

Personalized Opinion-Based Recommendation

“…The work of [20,15,21] is especially relevant and describes how shallow NLP, opinion mining, and sentiment analysis can be used to extract rich feature-based product descriptions (product cases) based on the features that users mention in their reviews, and also the polarity of their opinions. In order to generate user profiles and hotel descriptions, we follow four basic steps:…”

From More-Like-This to Better-Than-This

“…This paper builds on recent work on mining features and opinions from user reviews for recommender system [2]. In this section, we will outline how to use this information to build rich featurebased user and item descriptions based on the features that users mention in their reviews and the polarity of their opinions.…”

“…. , fm, from these reviews, based on the techniques described in [2]. Each feature, fj is associated with an importance score and a sentiment score as per Equations 2 and 3.…”

“…The features mentioned in these reviews, and the sentiment expressed by real-users, represent a powerful source of objective evaluation. Dong et al proposed [2] using this opinion information as the basis for hotel profiling. Intuitively, if a feature is mentioned by a user often, it may indicate that it is an important one.…”