1. Proceedings
  2. I3M
  3. 2020
  4. EMSS
  5. 10.46354/i3m.2020.emss.033

Using hybrid bayesian networks to detect audience behaviour changes in youtube

  • a Ezequiel Leonardo Castaño ,
  • b Guillermo Leale 
  • a,b Universidad Tecnológica Nacional Facultad Regional Rosario, Zeballos 1341, Rosario, C2000, Argentina
Cite as
Castaño E.L., Leale G. (2020). Using hybrid bayesian networks to detect audience behaviour changes in youtube. Proceedings of the 32nd European Modeling & Simulation Symposium (EMSS 2020), pp. 235-241. DOI: https://doi.org/10.46354/i3m.2020.emss.033

Abstract

The nowadays volatile fame one could gain from the Internet led to a disruption in the media industry, with important repercussions in platforms such as the educational channels from YouTube. In this work, one of such channels, which was shut down after more than 2 years of activity, is studied through the use of a Hybrid Bayesian Network with Markov Chain Monte Carlo based sampling. With the application of our model, the behaviour of users can be inferred and thus find whether it changed at some point. As a result, it was indeed possible not only to identify two specific moments in time when that changed but also to provide a transition zone between the steady states before and after the change.

References

  1. Aminikhanghahi, S. and Cook, D. J. (2017). A survey of methods for time series change point detection. Knowledge and information systems, 51(2):339–367.
  2. Arthurs, J., Drakopoulou, S., and Gandini, A. (2018). Researching YouTube.
  3. Bapin, Y. and Zarikas, V. (2019). Smart building’s elevator with intelligent control algorithm based on bayesian networks. Int. J. Adv. Comput. Sci. Appl.(IJACSA), 10(2):16–24.
  4. Cai, B., Kong, X., Liu, Y., Lin, J., Yuan, X., Xu, H., and Ji, R. (2018). Application of bayesian networks in reliability evaluation. IEEE Transactions on Industrial Informatics, 15(4):2146–2157.
  5. Castaño, E. L. (2020). Public Dataset for the Paper "Using Hybrid Bayesian Networks to Detect Audience Behaviour Changes in Youtube". 
  6. Corman, F. and Kecman, P. (2018). Stochastic prediction of train delays in real-time using bayesian networks. Transportation Research Part C: Emerging Technologies, 95:599–615.
  7. Davidson-Pilon, C. (2015). Bayesian methods for hackers: probabilistic programming and Bayesian inference. Addison-Wesley Professional.
  8. Dose, V. (2003). Bayesian inference in physics: case studies. Reports on Progress in Physics, 66(9):1421.
  9. Drury, B., Valverde-Rebaza, J., Moura, M.-F., and de Andrade Lopes, A. (2017). A survey of the applications of bayesian networks in agriculture. Engineering Applications of Artificial Intelligence, 65:29–42.
  10. Gamerman, D. and Lopes, H. F. (2006). Markov chain Monte Carlo: stochastic simulation for Bayesian inference. CRC Press. 
  11. Gelfand, A. E. and Smith, A. F. (1990). Sampling-based approaches to calculating marginal densities. Journal of the American statistical association, 85(410):398–409.
  12. Gelman, A., Rubin, D. B., et al. (1992). Inference from iterative simulation using multiple sequences. Statistical science, 7(4):457–472.
  13. Hastings, W. K. (1970). Monte Carlo sampling methods using Markov chains and their applications.
  14. Hoffman, M. D. and Gelman, A. (2014). The no-u-turn sampler: adaptively setting path lengths in hamiltonian monte carlo. Journal of Machine Learning Research, 15(1):1593–1623.
  15. Metropolis, N. (1987). The beginning of the. Los Alamos Science, 15:125–30.
  16. Ng, A. Y. and Jordan, M. I. (2002). On discriminative vs. generative classifiers: A comparison of logistic regression and naive bayes. In Advances in neural information processing systems, pages 841–848.
  17. O’hara, R. B. and Kotze, D. J. (2010). Do not logtransform count data. Methods in ecology and Evolution, 1(2):118–122
  18. Pearl, J. (1988). Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference. Morgan Kaufmann.
  19. Pourret, O., Naïm, P., and Marcot, B. (2008). Bayesian networks: a practical guide to applications. John Wiley & Sons.
  20. Salmerón, A., Rumí, R., Langseth, H., Nielsen, T. D., and Madsen, A. L. (2018). A review of inference algorithms for hybrid bayesian networks. Journal of Artificial Intelligence Research, 62:799–828.
  21. Salvatier, J., Wiecki, T. V., and Fonnesbeck, C. (2016). Probabilistic programming in python using PyMC3. PeerJ Computer Science, 2:e55.