An Interface Analysis for Building the Initial User Profile in Content-Based Recommendation Systems

• Nathália Locatelli Cezar State University of Santa Catarina (UDESC) http://orcid.org/0000-0003-2727-2121
• Isabela Gasparini State University of Santa Catarina (UDESC) https://orcid.org/0000-0002-8094-9261
• Daniel Lichtnow Federal University of Santa Maria (UFSM) https://orcid.org/0000-0003-0103-0538

DOI: https://doi.org/10.5753/sbbd_estendido.2024.243697

Abstract

A well-known problem in Recommender Systems is the Cold Start User, which refers to the fact that, when a user starts using a system, there is no information that allows generating good recommendations for this user. Some Recommender Systems seek to solve this by presenting items and asking users to evaluate these items. Here some questions involved are: (1) which items to select to be presented, (2) how many items are there and (3) how to present these items. This article discusses these issues a little and, in the case of the latter, presents an experiment and evaluation carried out with users.

Keywords: Recommender Systems, Cold Start User

References

Abdullah, N. A., Rasheed, R. A., Nizam, M. H., and Rahman, M. M. (2021). Eliciting auxiliary information for cold start user recommendation: A survey. Applied Sciences (Switzerland), 11(20).

Bettman, J. R., Luce, M. F., and Payne, J. W. (1998). Constructive Consumer Choice Processes. Journal of Consumer Research, 25(3):187–217.

Celma, O., Herrera, P., and Serra, X. (2006). Bridging the music semantic gap. CEUR Workshop Proceedings, 187:927–934.

Celma, Ó., Ramírez, M., and Herrera, P. (2005). Foafing the Music: A music recommendation system based on RSS feeds and user preferences. ISMIR 2005 - 6th International Conference on Music Information Retrieval, pages 464–467.

Cezar, N., Gasparini, I., Lichtnow, D., Lunardi, G., and de Oliveira, J. M. (2024). Exploring strategies to mitigate cold start in recommender systems: A systematic literature mapping. In Proceedings of the 26th International Conference on Enterprise Informa- tion Systems - Volume 1: ICEIS, pages 965–972. INSTICC, SciTePress.

Consoni, G. (2014). Recuperação de informação em sistemas de recomendação : análise da interação mediada por computador e dos efeitos da filtragem colaborativa na seleção de itens no website da Amazon.com. Tese - Programa de Pós Graduação em Comunicação e Informação da Universidade Federal do Rio Grande do Sul.

Goldberg, K., Roeder, T., Gupta, D., and Perkins, C. (2001). Eigentaste: A Constant Time Collaborative Filtering Algorithm. Information Retrieval, 4(2):133–151.

Jelassi, M. N., Ben Yahia, S., and Nguifo, E. M. (2013). A personalized recommender system based on users’ information in folksonomies. WWW 2013 Companion - Proceedings of the 22nd International Conference on World Wide Web, pages 1215–1223.

Monti, D., Rizzo, G., and Morisio, M. (2021). A systematic literature review of multicriteria recommender systems, volume 54. Springer Netherlands.

Panda, D. K. and Ray, S. (2022). Approaches and algorithms to mitigate cold start problems in recommender systems: a systematic literature review. Journal of Intelligent Information Systems, pages 341–366.

Ricci, F., Rokach, L., and Shapira, B. (2015). Recommender Systems.

Schafer, J. B., Frankowski, D., Herlocker, J., and Sen, S. (2007). Collaborative Filtering Recommender Systems, page 291–324. Springer-Verlag, Berlin, Heidelberg.

Son, L. H. (2016). Dealing with the new user cold-start problem in recommender systems: A comparative review. Information Systems, 58:87–104.