CienTec Guide: Application and Online Evaluation of a Context-Based Recommender System in Cultural Heritage
ResumoA Recommender System (RS) is best applied in situations where users have to decide to choose among a list of usually many options and visits in cultural heritage sites are an example of that. Visitors may also face problems in finding how to reach their options. This research addresses both problems with a mobile app consisting of a hybrid context-based RS that suggests personalized visiting routes with the goal to maximize user satisfaction and minimize the length of the recommended route. Unlike most published RS papers related to cultural heritage, the system in this research was built for the mobile platform and its effectiveness was evaluated with actual visitors of a museum. The results were consistent in indicating the improved system achieved high user satisfaction, with all the recommender attributes average ratings between 4.3 and 4.7 (in a scale of 1 to 5), and accuracy, with a Mean Average Error (MAE) of 0.69.
Benouaret, I. and Lenne, D. (2015). Personalizing the museum experience through context-aware recommendations. In 2015 IEEE International Conference on Systems, Man, and Cybernetics, pages 743–748.
Cao, L., Tao, J., and Bilian, C. (2018). Implementation of personalized scenic spots route recommendation system. pages 1–6.
Costa, A. F., Damico, J. S., Gonçalves, M. d. M., Cazelli, S., and Cruz, S. M. W. d. S. (2015). Museus de ciência e seus visitantes: pesquisa perfil-opinião 2013. Fundação Oswaldo Cruz / Casa de Oswaldo Cruz / Museu da Vida, Rio de Janeiro.
Fernández, L. E. M. (2018). Recommendation system for netflix. Technical report, Faculty of Science Business Analytics at Vrije Universiteit Amsterdam.
Guo, G., Zhang, J., Sun, Z., and Yorke-Smith, N. (2015). Librec: a java library for recommender systems. In UMAP Workshops.
Huang, Y.-M., Liu, C.-H., and Lee, C.-Y. (2012). Designing a personalized guide recommendation system to mitigate information overload in museum learning. Educational Technology and Society, 15:150–166.
Mathias, M., Moussa, A., Zhou, F., Torres-Moreno, J. M., Poli, M.-S., Josselin, D., El-Bèze, M., Linhares, A. C., and Rigat, F. (2014). Optimisation using natural language processing: personalized tour recommendation for museums. In 2014 Federated Conference on Computer Science and Information Systems, pages 439–446.
Pavlidis, G. (2019a). Recommender systems, cultural heritage applications, and the way forward. Journal of Cultural Heritage, 35:183 – 196. Modern and Contemporary Art.
Pavlidis, G. (2019b). Towards a novel user satisfaction modelling for museum visit recommender systems. In Duguleana, M., Carrozzino, M., Gams, M., and Tanea, I., editors, VR Technologies in Cultural Heritage, pages 60–75.
Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender systems handbook. Springer Publishing Company, Incorporated, 2nd edition.
Ricci, F., Rokach, L., Shapira, B., and Kantor, P. B. (2010). Recommender systems handbook. Springer-Verlag, Berlin, Heidelberg, 1st edition.
Rossi, S., Barile, F., Galdi, C., and Russo, L. (2016). Artworks sequences recommendations for groups in museums. In 2016 12th International Conference on Signal-Image Technology Internet-Based Systems (SITIS), pages 455–462.
van Hage, W. R., Stash, N., Wang, Y., and Aroyo, L. (2010). Finding your way through the rijksmuseum with an adaptive mobile museum guide. In Proceedings of the 7th International Conference on The Semantic Web: Research and Applications.
Wang, Y., Stash, N., Aroyo, L., Gorgels, P., Rutledge, L., and Schreiber, G. (2008). Recommendations based on semantically enriched museum collections. volume 6, pages 283 – 290. Semantic Web Challenge 2006/2007.