Towards a Collaborative Filtering Framework for Recommendation in Museums: From Preference Elicitation to Group's Visits

Abstract

Recommendation systems based on collaborative filtering methods can be exploited in the context of providing personalized artworks tours within a museum. However, in order to be effectively used, several problems have to be addressed: user preferences are not expressed as rating, items to be suggested are located in a physical space, and users may be in a group. In this work, we present a general framework that, by using the Matrix Factorization (MF) approach and a graph representation of a museum, addresses the problem of generating and then recommending an artworks sequence for a group of visitors within a museum. To reach a high-quality initial personalization, the recommendation system uses a simple, but efficient, elicitation method that is inspired by the MF approach. Moreover, the proposed approach considers the individual or the aggregated artworks’ ratings to build up a solution that takes into account the physical location of the artworks.