Recomendação de Conteúdo e QoE: Um Experimento Quantificando o Impacto da QoS nas Preferências por Conteúdos
Abstract
Recommender systems are increasingly present in Internet users's routine. Therefore, platforms like Youtube and Netflix seek to improve their recommendation systems, to provide a better experience for their users. The experience of users, however, depends on a multitude of factors. In particular, caching systems have an important influence in the quality of experience (QoE), since they impact quality of service (QoS) metrics (such as the delay and the throughput) experienced by users. In this paper, our goal is to devise a QoE-friendly recommender system. To this aim, we conduct an experiment with real users, having different profiles. Each users is requested to evaluate different movies, which vary in their contents and in the corresponding QoE. Our results provide a novel perspective on the relationships between recommender systems and caching systems. With decision trees, we propose a recommender system which accounts for QoE and content nature simultaneously. The proposed system reached a precision of 83% using our preliminary dataset which counts with hundreds of user ratings.
References
de Freitas, R. G., Menasché, D., Delgado, C., and Ziviani, A. (2017). Recomendação de conteúdo e desempenho de sistemas de cache.
Dehghan, M., Massoulie, L., Towsley, D., Menasche, D., and Tay, Y. C. (2016). A utility optimization approach to network cache design. In INFOCOM 2016, pages 1–9. IEEE.
Gomez-Uribe, C. A. and Hunt, N. (2016). The netix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems (TMIS), 6(4):13.
Krishnan, S. S. and Sitaraman, R. K. (2013). Video stream quality impacts viewer behavior: inferring causality using quasi-experimental designs. IEEE/ACM Transactions on Networking, 21(6):2001–2014.
Liu, D. and Yang, C. (2018). A learning-based approach to joint content caching and recommendation at base stations. arXiv preprint arXiv:1802.01414.
Mok, R. K., Chan, E. W., and Chang, R. K. (2011). Measuring the quality of experience of http video streaming. In Integrated Network Management (IM), 2011 IFIP/IEEE International Symposium on, pages 485–492. IEEE.
Nam, H., Kim, K.-H., and Schulzrinne, H. (2016). Qoe matters more than qos: Why people stop watching cat videos. In INFOCOM 2016, pages 1–9. IEEE.
Sermpezis, P., Spyropoulos, T., Vigneri, L., and Giannakas, T. (2017). Femto-caching with soft cache hits: Improving performance with related content recommendation. In GLOBECOM, pages 1–7. IEEE.
Turnbull, D. (2017). High-quality recommendation systems with elasticsearch. https://dzone.com/articles/high-quality-recommendation-systems-with-elastic-2.
