Analyzing the Retweeting Behavior of Influencers to Predict Popular Tweets, with and Without Considering their Content

  • Matías Gastón SilvaEmail author
  • Martín Ariel DomínguezEmail author
  • Pablo Gabriel CelayesEmail author
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 898)


Twitter and social networks in general, participate more and more in everyday life. This is why they have become a fundamental source of information that reflects the ideas and opinions of their users. This paper shows how the most influential users, called influencers, can be decisive in defining whether a publication becomes popular or not, regardless of its content. To achieve this, we build a dataset of Spanish-writing users sampled from Twitter, along with the content generated and shared by them within a year. In a first phase, we use different algorithms to detect users who are “influencers”. In a second phase, we train a binary classifier to predict if a given tweet will be a trending publication, based on information about the activity of the influencers on the given tweet. We obtain a model with an \(F_1\)-score close to \(79\%\), based on the retweeting behavior of a \(10\%\) of the users dataset considered as influencers. Finally, we add two Natural Language Processing (NLP) techniques to analyze the content: Twitter-LDA topic modeling, and FastText word embeddings. While both models alone have an \(F_1\) of less than \(50\%\) for trending prediction, FastText combined with the social model reaches an \(86.7\%\) score. We conclude that while analyzing the content can help to predict the popularity of a tweet, the influence of a user’s environment in the retweeting decision is surprisingly high.


Retweet prediction Social Network Analysis Machine learning LDA FastText Word embeddings 


  1. 1.
    Azcorra, A., et al.: Unsupervised scalable statistical method for identifying influential users in online social networks. Sci. Rep. 8, 6955 (2018)CrossRefGoogle Scholar
  2. 2.
    Bengio, Y.: Learning deep architectures for AI. Found. Trends Mach. Learn. 2(1), 1–127 (2009). Also published as a book. Now Publishers (2009)MathSciNetCrossRefGoogle Scholar
  3. 3.
    Bryan, K., Leise, T.: The \$25,000,000,000 eigenvector: the linear algebra behind google. SIAM Review 48, 569–581 (2006)MathSciNetCrossRefGoogle Scholar
  4. 4.
    Buckley, F., Harary, F.: Distance in Graphs. Addison-Wesley, Boston (1990)zbMATHGoogle Scholar
  5. 5.
    Cardelino, C.: Spanish billion word corpus and embeddings.
  6. 6.
    Celayes, P.G., Domínguez, M.A.: Prediction of user retweets based on social neighborhood information and topic modelling. In: Castro, F., Miranda-Jiménez, S., González-Mendoza, M. (eds.) MICAI 2017. LNCS (LNAI), vol. 10633, pp. 146–157. Springer, Cham (2018). Scholar
  7. 7.
    Cossu, J.V., Dugué, N., Labatut, V.: Detecting real-world influence through Twitter. In: 2015 Second European Network Intelligence Conference, pp. 83–90 (2015)Google Scholar
  8. 8.
    Csardi, G., Nepusz, T.: The igraph software package for complex network research. Int. J. Complex Syst. 1695, 1–9 (2006). Scholar
  9. 9.
    Freeman, L.C.: A set of measures of centrality based on betweenness. Sociometry 40(1) (1977)CrossRefGoogle Scholar
  10. 10.
    Grave, E., Mikolov, T., Joulin, A., Bojanowski, P.: Bag of tricks for efficient text classification. In: Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2017, pp. 427–431, Spain (2017).
  11. 11.
    Hochreiter, R., Waldhauser, C.: A genetic algorithm to optimize a tweet for retweetability. Mendel, pp. 13–18 (2013)Google Scholar
  12. 12.
    Honnibal, M., Johnson, M.: An improved non-monotonic transition system for dependency parsing. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1373–1378. ACL, Portugal (2015).
  13. 13.
    Smith, J.E., Tahir, M., Sannen, D., van Brussel, H.: Making early prediction of the accuracy of machine learning applications. In: Lughofer, E., Sayed-Mouchaweh, M. (eds.) Learning in Non-stationary Environments: Methods and Applications, pp. 121–151. Springer, New York (2012). Scholar
  14. 14.
    Lau, J.H., Baldwin, T.: An empirical evaluation of doc2vec with practical insights into document embedding generation. In: Proceedings of the 1st Workshop on Representation Learning for NLP, pp. 78–86. Association for Computational Linguistics (2016)Google Scholar
  15. 15.
    Mikolov, T., Chen, K., Corrado, G., Dean, J.: Efficient estimation of word representations in vector space. CoRR abs 1301.3781 (2013)Google Scholar
  16. 16.
    Morone, F., Min, B., Bo, L., Mari, R., Makse, H.A.: Collective influence algorithm to find influencers via optimal percolation in massively large social media. Sci. Rep. 6, 30062 (2016)CrossRefGoogle Scholar
  17. 17.
    Nasir, N., Gottron, T., Kunegis, J., Alhadi, A.C.: Bad news travel fast: a content-based analysis of interestingness on Twitter. In: Proceedings of the 3rd International Conference on Web Science, WebSci 2011 (2011)Google Scholar
  18. 18.
    Naveed, N., Gottron, T., Kunegis, J., Alhadi, A.C.: Bad news travel fast: a content-based analysis of interestingness on Twitter. In: Proceedings of the 3rd International Web Science Conference, WebSci 2011, pp. 8:1–8:7. ACM, New York (2011)Google Scholar
  19. 19.
    Neves, A., Vieira, R., Mourão, F., Rocha, L.: Quantifying complementarity among strategies for influencers’ detection on Twitter1. Procedia Comput. Sci. 51, 2435–2444 (2015). International Conference on Computational Science, ICCS 2015CrossRefGoogle Scholar
  20. 20.
    Page, L., Brin, S., Motwani, R., Winograd, T.: The pagerank citation ranking: bringing order to the web. Stanford University, Technical report (1999)Google Scholar
  21. 21.
    Pedregosa, F., et al.: Scikit-learn: machine learning in Python. J. Mach. Learn. Res. 12, 2825–2830 (2011). Scholar
  22. 22.
    Pennacchiotti, M., Popescu, A.M.: A machine learning approach to Twitter user classification. In: Proceedings of the Fifth International Conference on Weblogs and Social Media, Barcelona, Catalonia, vol. 11, Spain (2011)Google Scholar
  23. 23.
    Sabidussi, G.: The centrality index of a graph. Psychometrika 31(4), 581–603 (1966)MathSciNetCrossRefGoogle Scholar
  24. 24.
    Arora, S., Liang, Y., Ma, T.: A simple but tough-to-beat baseline for sentence embeddings. In: Proceeding of International Conference on Learning Representations, ICLR 2017, Toulon, France, 24–26 April (2017)Google Scholar
  25. 25.
    Simmie, D.S., Vigliotti, M.G., Hankin, C.: Ranking Twitter influence by combining network centrality and influence observables in an evolutionary model. J. Complex Netw. 2(4), 495–517 (2014)CrossRefGoogle Scholar
  26. 26.
    Uddin, M.M., Imran, M., Sajjad, H.: Understanding types of users on Twitter. CoRR abs/1406.1335 (2014)Google Scholar
  27. 27.
    Vosoughi, S., Roy, D., Aral, S.: The spread of true and false news online. Science 359(6380), 1146–1151 (2018)CrossRefGoogle Scholar
  28. 28.
    Vougioukas, M., Androutsopoulos, I., Paliouras, G.: Identifying retweetable tweets with a personalized global classifier. In: Proceedings of the 10th Hellenic Conference on Artificial Intelligence, SETN 2018, Patras, Greece, 09–12 July 2018, pp. 8:1–8:8 (2018).
  29. 29.
    Zhang, J., Brackbill, D., Yang, S., Centola, D.: Efficacy and causal mechanism of an online social media intervention to increase physical activity: results of a randomized controlled trial. PM Rep. 2, 651–657 (2015)Google Scholar
  30. 30.
    Zhao, W.X., et al.: Comparing Twitter and traditional media using topic models. In: Clough, P., et al. (eds.) ECIR 2011. LNCS, vol. 6611, pp. 338–349. Springer, Heidelberg (2011). Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.FaMAF, Universidad Nacional de CordobaCórdobaArgentina

Personalised recommendations