Group Recommendations Based on Hesitant Fuzzy Sets. Issue 10 (11th July 2017)

• Record Type: Journal Article
• Authors: Castro, Jorge; Barranco, Manuel J.; Rodríguez, Rosa M.; Martínez, Luis
• Other Names: De Tré Guy guestEditor.; Kacprzyk Janusz guestEditor.; Pasi Gabriella guestEditor.; Zadrożny Sławomir guestEditor.; Bronselaer Antoon guestEditor.
• Is Part Of: International journal of intelligent systems. Volume 33:Issue 10(2018)
• Page Start: 2058
• Page End: 2077
• Publication Date: 2017-07-11
• Subjects: Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; 006.3
• DOI: 10.1002/int.21922
• Languages: English
• ISSNs: 0884-8173

Abstract

Abstract: Group recommender systems (GRSs) recommend items that are used by groups of people because certain activities, such as listening to music, watching a movie, dining in a restaurant, etc., are social events performed by groups of people sharing their tastes, and their choices affect all of them. GRSs help groups of people making choices in overloaded search spaces according to all group members preferences. A common GRS scheme aggregates users preferences to generate a group preference profile. However, the aggregation process may imply a loss of information, negatively affecting different properties of the GRS such as diversity of group recommendations, which is an important quality factor because of such recommendations are targeted to groups formed by users with individual and possibly conflicting preferences. To avoid and manage the loss of information caused by aggregation, this paper proposes to keep all group members preferences by using hesitant fuzzy sets (HFSs) and interpreting such information like the group hesitation about their preferences that will be used in the group recommendation process. To evaluate the performance and rank quality of the HFS GRS proposal, a case study is carried out.