Previsão de Engajamento de Usuários Durante Transmissão Adaptativa de Vídeo ao Vivo

• Thiago Guarnieri UFMG
• Alex Vieira UFJF
• Ítalo Cunha UFMG
• Jussara Almeida UFMG

DOI: https://doi.org/10.5753/sbrc.2018.2414

Abstract

The recent efforts in developing adaptive algorithms and user allocation management tools have contributed significantly to the increase on the quality of experience (QoE) in Internet live video. However, a considerable fraction of sessions still suffer from low QoE, which may reduce user engagement. This problem persists because service providers cannot predict when users will leave the system and attempt to prevent their departure. In this work, we propose a pipelined model for predicting user engagement based on independent variables historically related to QoE. User sessions are clustered by their performance similarities. For each cluster, regression and decision tree based models are built to predict (1) the remaining session time and (2) whether the user will remain watching for the next n minutes. Experiments with real datasets show significant accuracy in the prediction of remaining session time and user permanence, which demonstrates the feasibility of using performance metrics to predict user engagement.

References

Ahmed, A., Shaq, Z., Bedi, H., and Khakpour, A. (2017). Suffering from buffering? detecting QoE impairments in live video streams. In 2017 IEEE 25th International Conference on Network Protocols (ICNP), pages 1–10.

Ahmed, A., Shaq, Z., and Khakpour, A. (2016). QoE analysis of a large-scale live video streaming event. In Proc. of the 2016 ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Science, pages 395–396.

Almeida, B., Carnivalli, G., de Almeida Junior, W., Almeida, J., Cunha, I., and Vieira, A. B. (2016). Caracterização do comportamento dos clientes de um sistema de vídeo ao vivo durante um evento de larga escala na internet. In 34o. Simpósio Brasileiro de Redes de Computadores e Sistemas Distribuídos.

Apple (2016). HTTP Live Streaming (HLS) Apple Developer. http://developer.apple.com/streaming.

Balachandran, A., Sekar, V., Akella, A., Seshan, S., Stoica, I., and Zhang, H. (2013). Developing a predictive model of quality of experience for internet video. SIGCOMM Comput. Commun. Rev., 43(4):339–350.

Casas, P., Seufert, M., and Schatz, R. (2013). Youqmon: A system for on-line monitoring of youtube QoE in operational 3g networks. ACM SIGMETRICS Performance Evaluation Review, 41(2):44–46.

Chen, Y., Chen, Q., Zhang, F., Zhang, Q., Wu, K., Huang, R., and Zhou, L. (2015). Understanding viewer engagement of video service in wi- network. Computer Networks, 91:101–116.

Cisco, V. N. I.(2017). The zettabyte era: Trends and analysis.

Cisco whitepaper (june, 2017), [link].

Costa, C., Cunha, I., Borges, A., Ramos, C., Rocha, M., Almeida, J., and Ribeiro-Neto, B. (2004). Analyzing client interactivity in streaming media. In Proceedings of the 13th ACM international conference on World Wide Web, pages 534–543.

da Costa Filho, R. I. T., Lautenschlager, W., Kagami, N., Roesler, V., and Gaspary, L. P. (2016). Network fortune cookie: Using network measurements to predict video streaming performance and QoE. In Proc. of the IEEE GLOBECOM.

Duanmu, Z., Rehman, A., Zeng, K., and Wang, Z. (2016). Quality-of-experience prediction for streaming video. In Proc. of the IEEE ICME.

Gill, P., Arlitt, M., Li, Z., and Mahanti, A. (2007). Youtube trafc characterization: a view from the edge. In Proceedings of the 7th ACM SIGCOMM conference on Internet measurement, pages 15–28.

Guarnieri, T., Ítalo Cunha, Almeida, J., Drago, I., and Vieira, A. B. (2017). Characterizing QoE in large-scale live streaming. In Proc. of the IEEE GLOBECOM.

Ho, T. K. (1995). Random decision forests. In Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) Volume 1, ICDAR ’95, pages 278–.

Hossfeld, T., Egger, S., Schatz, R., Fiedler, M., Masuch, K., and Lorentzen, C. (2012). Initial delay vs. interruptions: Between the devil and the deep blue sea. In 2012 Fourth International Workshop on Quality of Multimedia Experience, pages 1–6.

Juluri, P., Tamarapalli, V., and Medhi, D. (2016). Measurement of quality of experience IEEE Communications Surveys Tutorials, of video-on-demand services: A survey. 18(1):401–418.

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.

Macqueen, J. (1967). Some methods for classication and analysis of multivariate observations. In In 5-th Berkeley Symposium on Mathematical Statistics and Probability, pages 281–297.

Mann, H. and Whitney, D. (1947). On a test of whether one of two random variables is stochastically larger than the other. Annals of Mathematical Statistics, 18:50–60. Mao, H., Netravali, R., and Alizadeh, M. (2017). Neural adaptive video streaming with pensieve. In Proceedings of the Conference of the ACM Special Interest Group on Data Communication, SIGCOMM ’17, pages 197–210.

Oshiro, T. M., Perez, P. S., and Baranauskas, J. A. (2012). How Many Trees in a Random Forest?, pages 154–168. Springer Berlin Heidelberg, Berlin, Heidelberg.

Pelleg, D. and Moore, A. W. (2000). X-means: Extending k-means with efcient estimation of the number of clusters. In Seventeenth International Conference on Machine Learning, pages 727–734. Morgan Kaufmann.

Qi, Y. and Dai, M. (2006). The effect of frame freezing and frame skipping on video quality. In 2006 International Conference on Intelligent Information Hiding and Multimedia, pages 423–426.

Schwarz, G. E. (1978). Estimating the dimension of a model. Annals of Statistics, 6(2):461–464.

Seufert, M., Egger, S., Slanina, M., Zinner, T., Hoßfeld, T., and Tran-Gia, P. (2015). A IEEE Communications survey on quality of experience of http adaptive streaming. Surveys Tutorials, 17(1):469–492.

Shaq, M. Z., Erman, J., Ji, L., Liu, A. X., Pang, J., and Wang, J. (2014). Understanding the impact of network dynamics on mobile video user engagement. In ACM SIGMETRICS Performance Evaluation Review, volume 42, pages 367–379.

Stockhammer, T. (2011). Dynamic adaptive streaming over http–: standards and design principles. In Proceedings of the second annual ACM conference on Multimedia systems, pages 133–144. ACM.

Vriendt, J. D., Vleeschauwer, D. D., and Robinson, D. (2013). Model for estimating QoE In 2013 IFIP/IEEE International of video delivered using http adaptive streaming. Symposium on Integrated Network Management (IM 2013), pages 1288–1293.

Yin, X., Jindal, A., Sekar, V., and Sinopoli, B. (2015). A control-theoretic approach for dynamic adaptive video streaming over http. In Proc. of the ACM Conference on Special Interest Group on Data Communication, SIGCOMM ’15, pages 325–338.