Multi-Criteria Review-Based Recommender System–The State of the Art

Abstract

In recent times, the recommender systems (RSs) have considerable importance in academia, commercial activities, and industry. They are widely used in various domains such as shopping (Amazon), music (Pandora), movies (Netflix), travel (TripAdvisor), restaurant (Yelp), people (Facebook), and articles (TED). Most of the RSs approaches rely on a single-criterion rating (overall rating) as a primary source for the recommendation process. However, the overall rating is not enough to gain high accuracy of recommendations because the overall rating cannot express fine-grained analysis behind the user's behavior. To solve this problem, multi-criteria recommender systems (MCRSs) have been developed to improve the accuracy of the RS performance. Additionally, a new source of information represented by the user-generated reviews is incorporated in the recommendation process because of the rich and numerous information included (i.e. review elements) related to the whole item or to a certain feature of the item or the user's preferences. The valuable review elements are extracted using either text mining or sentiment analysis. MCRSs benefit from the review elements of the user-generated reviews in building their criteria forming multi-criteria review based recommender systems. The review elements improve the accuracy of the RS performance and mitigate most of the RS's problems such as the cold start and sparsity. In this review, we focused on the multi-criteria review-based recommender system and explained the user reviews elements in detail and how these can be integrated into the RSs to help develop their criteria to enhance the RSs performance. Finally, based on the survey, we presented four future trends based on this type of RSs to support researchers who wish to pursue studies in this area. INDEX TERMS Recommender system, multi-criteria recommender system, user-generated reviews, review elements, sentiment analysis, text mining, multi-criteria review-based recommender system, recommender system accuracy.

A Physical Activity Recommender System for Patients With Arterial Hypertension

“…The essence of a recommender system is the modeling of the user's profile and the discovery of knowledge about consumption habits, preferences, behavior and lifestyle [13]. These characteristics are fundamental for a system to generate recommendations assertively [14]. In the health context, some of these solutions have already been developed [15], [16].…”

Unsupervised Semantic Approach of Aspect-Based Sentiment Analysis for Large-Scale User Reviews

“…The datasets of the book and movie domains are from the Amazon dataset, whereas the restaurant domain is from the Yelp dataset. The number of user reviews used in the experiments are 1,500,000, 1 http://jmcauley.ucsd.edu/data/amazon/links.html 1,300,000, and 1,000,000 for the book, movie, and restaurant domains, respectively. The results for each task mentioned in the methodology section are presented and discussed in the following sections.…”

“…[ 43 ] It was claimed that learned aspects (i.e., aspects extracted from the reviews) generate better overall sentiment results as compared to the fixed predefined aspects. This is due to the fact that the number of the aspects in the fixed pre-defined list is limited, and there is no guarantee that these aspects will occur in the users' reviews [1,44]. As a result, few researchers use the vocabulary-based method.…”

“…Such reviews are considered a valuable resource for both consumers and businesses. Despite the benefit of these reviews, the extraction of useful information from such reviews is a huge challenge due to its large scale and distinct characteristics [1]. Research to overcome such issues have been proposed by many fields, which, among others, were related to mining distinct and important information [2][3][4], extracting users' sentiments [5,6] or summarizing user reviews [7,8].…”

“…It has an obvious effect in many applications when the aspects are extracted efficiently with their opinions' values. For example, they can be used to construct user and item profiles in decision-making processes, such as recommender systems [1,14], or to construct a domain ontology [15]. Additionally, it has been used in many systems for different purposes such as tourism [16], online education [17], and transportation [18].…”