The Utility Problem of Web Content Popularity Prediction

ABSTRACT

The ability to generate and share content on social media platforms has changed the Internet. With the growing rate of content generation, efforts have been directed at making sense of such data. One of the most researched problem concerns predicting web content popularity. We argue that the evolution of state-of-the-art approaches has been optimized towards improving the predictability of average behaviour of data: items with low levels of popularity. We demonstrate this effect using a utility-based framework for evaluating numerical web content popularity prediction tasks, focusing on highly popular items. Additionally, it is demonstrated that gains in predictive and ranking ability of such type of cases can be obtained via naïve approaches, based on strategies to tackle imbalanced domains learning tasks.

References

1. N. S. Altman. 1992. An Introduction to Kernel and Nearest-Neighbor Nonparametric Regression. The American Statistician Vol. 46, 3 (1992), 175--185.
2. S. Asur and B. A. Huberman. 2010. Predicting the Future with Social Media. In Proc. of 2010 Int. Conf. on Web Intelligence and Intelligent Agent Technology (WI-IAT '10). IEEE Computer Society, Washington, DC, USA, 492--499.
3. P. Branco, L. Torgo, and R. P. Ribeiro. 2016. A Survey of Predictive Modeling on Imbalanced Domains. ACM Comput. Surv., Vol. 49, 2, Article bibinfoarticleno31 (Aug.. 2016).
4. J. Demvsar. 2006. Statistical comparisons of classifiers over multiple data sets. JMLR, Vol. 7, Jan (2006), 1--30.
5. R. L. Dougherty, A. Edelman, and J. M. Hyman. 1989. Nonnegativity-, Monotonicity-, or Convexity-Preserving Cubic and Quintic Hermite Interpolation. Math. Comp. Vol. 52, 186 (1989), 471--494.
6. K. J"arvelin and J. Kek"al"ainen. 2000. IR Evaluation Methods for Retrieving Highly Relevant Documents Proc. of the 23rd ACM SIGIR. 41--48.
7. N. Moniz and L. Torgo. 2018. Multi-Source Social Feedback of Online News Feeds. CoRR Vol. abs/1801.07055 (2018).
8. N. Moniz, L. Torgo, M. Eirinaki, and P. Branco. 2017. A Framework for Recommendation of Highly Popular News Lacking Social Feedback. New Generation Computing Vol. 35, 4 (2017), 417--450.
9. E. A. Nadaraya. 1964. On Estimating Regression. Theory of Probability & Its Applications Vol. 9, 1 (1964), 141--142.
10. H. Pinto, J. M. Almeida, and M. A. Gonccalves. 2013. Using Early View Patterns to Predict the Popularity of Youtube Videos Proc. of 6th ACM Int. Conf. WSDM (WSDM '13). ACM, New York, NY, USA, 365--374.
11. R. Ribeiro. 2011. Utility-based Regression. Ph.D. Dissertation. bibinfoschoolDep. Computer Science, Faculty of Sciences - University of Porto.
12. B. Shulman, A. Sharma, and D. Cosley. 2016. Predictability of Popularity: Gaps between Prediction and Understanding Proc. of 10th ICWSM. AAAI, Cologne, Germany, 348--357.
13. G. Szabo and B. A. Huberman. 2010. Predicting the Popularity of Online Content. Commun. ACM, Vol. 53, 8 (Aug.. 2010), 80--88.
14. A. Tatar, M. D. de Amorim, S. Fdida, and P. Antoniadis. 2014. A survey on predicting the popularity of web content. JIAS, Vol. 5, 1 (2014), 1--20.
15. A. Tatar, J. Leguay, P. Antoniadis, A. Limbourg, M. D. de Amorim, and S. Fdida. 2011. Predicting the Popularity of Online Articles Based on User Comments Proc. of 2011 WIMS (WIMS '11). ACM, New York, NY, USA, Article bibinfoarticleno67.
16. L. Torgo. 2014. An Infra-Structure for Performance Estimation and Experimental Comparison of Predictive Models in R. CoRR Vol. abs/1412.0436 (2014), 1--40.
17. J. W. Tukey. 1977. Exploratory Data Analysis. Addison-Wesley, Princeton, NJ.
18. Q. Yang and X. Wu. 2006. 10 challenging problems in data mining research. Int. J. of Inf. Tech. & Dec. Mak. Vol. 05, 04 (2006), 597--604.