Recommender System Based on Consumer Product Reviews

Consumer reviews, opinions and shared experiences in the use of a product is a powerful source of information about consumer preferences that can be used in recommender systems. Despite the importance and value of such information, there is no comprehensive mechanism that formalizes the opinions selection and retrieval process and the utilization of retrieved opinions due to the difficulty of extracting information from text data. In this paper, a new recommender system that is built on consumer product reviews is proposed. A prioritizing mechanism is developed for the system. The proposed approach is illustrated using the case study of a recommender system for digital cameras

Reliable entertainment: Spanish consumers' preferences regarding a film's country of origin

This article contributes to the study of cinema audiences in Europe by analyzing the actual behavior of Spanish moviegoers and their level of satisfaction. We modeled moviegoers’ choice of film by country of origin (U.S.A., Spain, and other countries) according to a set of determinants: (1) consumers’ interpretation of several sources of information, (2) motivations and (3) choice rules. We found three clear consumer stereotypes related to each type of film: (1) U.S.A. films were preferred by almost everyone (especially families and younger audiences); (2) Spanish films had audiences composed of middle-age and middle-class moviegoers; and (3) European productions were preferred by a social or intellectual elite. U.S.A. films dominate the Spanish market for the reason that they provide most of what moviegoers prefer, namely, familiar, reliable entertainment in Spanish; three characteristics that are not satisfied by Spanish and European films. Additionally, we discuss the implications for the European cultural policy

Informed recommender: basing recommendations on consumer product reviews

Recommender systems attempt to predict items in which a user might be interested, given some information about the user's and items' profiles. Most existing recommender systems use content-based or collaborative filtering methods or hybrid methods that combine both techniques (see the sidebar for more details). We created Informed Recommender to address the problem of using consumer opinion about products, expressed online in free-form text, to generate product recommendations. Informed recommender uses prioritized consumer product reviews to make recommendations. Using text-mining techniques, it maps each piece of each review comment automatically into an ontology