On January 22, 2021, Mayeul Matthias will defend his thesis entitled “Recommendation of Personalized Cultural Paths – An Interdisciplinary Study of Automated Visit Proposals.” This thesis is supervised by Juan-Manuel Torres and Didier Josselin, and co-supervised by Fen Zhou.
The jury consists of:
- Patrice BELLOT – Aix-Marseille Université, LIS (Rapporteur)
- Sébastien MUSTIÈRE – Université Gustave-Eiffel/ENSG, IGN (Rapporteur)
- Marie-Sylvie POLI – Avignon Université, LCC (Examinatrice)
- Enrico NATALIZIO – Université de Lorraine, LORIA (Examinateur)
- Francesco DE PELLEGRINI – Avignon Université, LIA (Président)
- Juan-Manuel TORRES-MORENO (Directeur)
- Didier JOSSELIN – Avignon Université, ESPACE (Co-directeur)
- Fen ZHOU (Co-Encadrant)
Abstract: This thesis focuses on recommending cultural visits through an interdisciplinary approach. These works combine techniques from Operations Research and natural language processing while drawing on concepts from audience sociology and geography. We propose new methods for evaluating cultural points of interest and automatically creating tourist routes that take into account the desires expressed by a visitor. These principles are applied on two different scales and contexts: museum visits and cultural paths within a city.
In the first part, we concentrate on visits to art museums based on the preferences expressed by the visitor and the prestige of the artworks. This dual approach allows classifying the works both according to the cultural affinities of the visitor and their importance within the museum. The latter is calculated by applying automatic text summarization algorithms to the museum’s official descriptions of the works, providing a visit profile reflecting the discovery of a museum through its masterpieces. This profile can then be adjusted according to the visitor’s preferences to obtain a visit that corresponds to them while preserving the “museum’s perspective.”
Subsequently, we liken the construction of a route to a routing problem, aiming to find a path among different rooms and artworks that maximizes visitor satisfaction while respecting time constraints. Two methods are proposed: an integer linear programming model and a heuristic that can be used for real-time route proposals, for example, upon their arrival at the museum.
In the second part, we delve into tourist recommendations within a city by establishing metrics to construct a route. Through an interdisciplinary study, we highlight the importance of personalized routes and identify an essential factor during their construction, besides cultural tastes: the visit pace. A new method of measuring the quality of a route’s experience encompassing these two criteria is employed. This method unites approaches from literature for assessing cultural interest and utilizes actograms as a geographical representation of a route, thereby defining a measure of visit pace.
Subsequently, we develop a system for recommending tourist visits in the form of an integer linear programming model based on an extensible formalism capable of considering a wide variety of constraints. It integrates three criteria for evaluating the route: cultural interest and visit pace, which depend on tourist preferences and are measured at different scales to introduce coherence in route construction. Additionally, we propose incorporating the apex-end effect into the objective function, a famous psychological heuristic that has been applied in numerous other domains.
Based on concrete case studies, we demonstrate that the combined use of techniques from various disciplines yields good results, both in estimating the appeal of points of interest and in constructing tourist routes.