A peek into the future: predicting the evolution of popularity in user generated content

  • Authors:

  • Mohamed Ahmed;Stella Spagna;Felipe Huici;Saverio Niccolini

  • Affiliations:

  • NEC Laboratories Europe, Heidelberg, Germany;Univ. of Pisa, Pisa, Italy;NEC Laboratories Europe, Heidelberg, Germany;NEC Laboratories Europe, Heidelberg, Germany

  • Venue:
  • Proceedings of the sixth ACM international conference on Web search and data mining
  • Year:
  • 2013

Quantified Score

Hi-index 0.00

Visualization

Abstract

Content popularity prediction finds application in many areas, including media advertising, content caching, movie revenue estimation, traffic management and macro-economic trends forecasting, to name a few. However, predicting this popularity is difficult due to, among others, the effects of external phenomena, the influence of context such as locality and relevance to users,and the difficulty of forecasting information cascades. In this paper we identify patterns of temporal evolution that are generalisable to distinct types of data, and show that we can (1) accurately classify content based on the evolution of its popularity over time and (2) predict the value of the content's future popularity. We verify the generality of our method by testing it on YouTube, Digg and Vimeo data sets and find our results to outperform the K-Means baseline when classifying the behaviour of content and the linear regression baseline when predicting its popularity.