Semantic Graph-Based Recommender System. Application in Cultural Heritage

Abstract

Research on visitor support systems for museums and cultural sites has been particularly important in recent years. Many research projects have been created to assist the visitor before and during his visit. The cultural heritage area is affected by the problem of information overload. With the advent of the social web, a large number of available resources have emerged coming from the social information systems SocIS. Therefore, visitors are swamped with enormous choices in their visited cities. Even though, SocIS platforms use the features of collaborative tagging, named folksonomy, to commonly contribute to the management of the shared resources. Collaborative tagging lacks semantic which reduces the effectiveness of organizing resources. It decreases their findability and discoverability, thereby their recommendation. In this paper, we aim to personalize the cultural heritage visit, i.e., to suggest semantically related places that are most likely to interest a visitor. Our proposed approach represents a semantic graph-based recommender system of cultural heritage places by (1) constructing an emergent semantic description that semantically augments the place and (2) effectively modeling the emerging graphs representing the semantic relatedness of similar cultural heritage places and their related tags. The experimental evaluation shows relevant results attesting the efficiency of our proposal applied to recommend cultural heritage of Marrakesh city. Future perspectives will focus on creating a real-world application using augmented reality. It will include a semantic-based context-aware recommender system that rises in value the cultural heritage of the touristic city by suggesting historical places that suit the visitor’s interests.