A Network-Based Model for Predicting Hashtag Breakouts in Twitter

  • Sultan Alzahrani
  • Saud Alashri
  • Anvesh Reddy Koppela
  • Hasan DavulcuEmail author
  • Ismail Toroslu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 9021)


Online information propagates differently on the web, some of which can be viral. In this paper, first we introduce a simple standard deviation sigma levels based Tweet volume breakout definition, then we proceed to determine patterns of re-tweet network measures to predict whether a hashtag volume will breakout or not. We also developed a visualization tool to help trace the evolution of hashtag volumes, their underlying networks and both local and global network measures. We trained a random forest tree classifier to identify effective network measures for predicting hashtag volume breakouts. Our experiments showed that “local” network features, based on a fixed-sized sliding window, have an overall predictive accuracy of 76 %, where as, when we incorporate “global” features that utilize all interactions up to the current period, then the overall predictive accuracy of a sliding window based breakout predictor jumps to 83 %.


Information diffusion Hashtag volumes Prediction  Social networks Diffusion networks 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Li, C., Sun, A., Datta, A.: Twevent: segment-based event detection from tweets. In: Proceedings of the 21st ACM International Conference on Information and Knowledge Management, pp. 155–164. ACM (2012)Google Scholar
  2. 2.
    Newman, M.E.J. A measure of betweenness centrality based on random walks. Social networks 27.1, 39–54 (2005)Google Scholar
  3. 3.
    Brin, S., Page, L.: The anatomy of a large-scale hypertextual Web search engine. Computer Networks and ISDN Systems 30, 107–117 (1998). doi: 10.1.16/S0169-7552(98)00110-X CrossRefGoogle Scholar
  4. 4.
    Barrat, A., Barthelemy, M., Pastor-Satorras, R., Vespignani, A.: The architecture of complex weighted networks. In: Proceedings of the National Academy of Sciences of the United States of America 101.11, PP. 3747–3752 (2004)Google Scholar
  5. 5.
    Weng, L., Menczer, F., Ahn, Y.-Y.: Virality prediction and community structure in social networks. Scientific reports 3 (2013)Google Scholar
  6. 6.
    Freeman, L.C.: A set of measures of centrality based on betweenness.Sociometry, 35–41 (1977)Google Scholar
  7. 7.
    Arruda, G., Barbieri, A., Rodrigues, F., Moreno, Y., Costa, L.: The role of centrality for the identification of influential spreaders in complex networks. Physical Review E 90, 032812 (2014)CrossRefGoogle Scholar
  8. 8.
    Cheng, J., Adamic, L., Dow, P.A., Kleinberg, J.M., Leskovec, J.: Can cascades be predicted?. In: Proceedings of the 23rd International Conference on World Wide Web, pp. 925–936. International World Wide Web Conferences Steering Committee (2014)Google Scholar
  9. 9.
    Pearson, K.: LIII. On lines and planes of closest fit to systems of points in space. The London, Edinburgh, and Dublin Philosophical Magazine and Journal of Science 2(11), 559–572 (1901)Google Scholar
  10. 10.
    Bandalos, D.L., Boehm-Kaufman, M.R.: Four common misconceptions in exploratory factor analysis. Statistical and methodological myths and urban legends: Doctrine, verity and fable in the organizational and social sciences, 61–87 (2009)Google Scholar
  11. 11.
    Asur, S., et al.: Trends in social media: persistence and decay. ICWSM (2011)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Sultan Alzahrani
    • 1
  • Saud Alashri
    • 1
  • Anvesh Reddy Koppela
    • 1
  • Hasan Davulcu
    • 1
    Email author
  • Ismail Toroslu
    • 2
  1. 1.School of Computing, Informatics and Decision Systems EngineeringArizona State UniversityTempeUSA
  2. 2.Department of Computer EngineeringMiddle East Technical UniversityAnkaraTurkey

Personalised recommendations