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

• DOI: 10.1016/j.procs.2016.09.067
• Publication Date: 2016-09-21T08:34:53Z
• Authors: Silvia Rossi; Francesco Barile; Davide Improta; Luca Russo
• Keywords: Representation

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