Skip to main content
SpringerLink
Log in

Exploring the collective human behavior in cascading systems: a comprehensive framework

  • Regular Paper
  • Published:
Knowledge and Information Systems Aims and scope Submit manuscript

Abstract

The collective behavior describing spontaneously emerging social processes and events is ubiquitous in both physical society and online social media. The knowledge of collective behavior is critical in understanding and predicting social movements, fads, riots, and so on. However, detecting, quantifying, and modeling the collective behavior in cascading systems at large scale are seldom explored. In this paper, we examine a real-world online social media with more than 1.7 million information spreading records. We observe evident collective behavior in information cascading systems and then propose metrics to quantify the collectivity. We find that previous information cascading models cannot capture the collective behavior in the real-world data and thus never utilize it. Furthermore, we propose a comprehensive generative framework with a latent user interest layer to capture the collective behavior. Our framework accurately models the information cascades with respect to dynamics, popularity, structure, and collectivity. By leveraging the knowledge behind collective behavior, our model successfully predicts the popularity and participants of information cascades without temporal features or early stage information. Our framework may serve as a more generalized one in modeling cascading systems, and, together with empirical discovery and applications, advance our understanding of human behavior.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10

Similar content being viewed by others

Notes

  1. The 5 periods include: morning(6:00–10:00), noon(10:00–14:00), afternoon(14:00–18:00), evening(18:00–22:00), and night(22:00–6:00 nextday).

  2. http://t.qq.com/

References

  1. Banerjee S, Agarwal N (2012) Analyzing collective behavior from blogs using swarm intelligence. Knowl Inf Syst 33(3):523–547

    Article  Google Scholar 

  2. Bian J, Yang Y, Chua, TS (2014) Predicting trending messages and diffusion participants in microblogging network. pp 537–546

  3. Calabrese F, Giusy DL, Ratti C (2010) Human mobility prediction based on individual and collective geographical preferences. In: 2010 13th international IEEE conference on IEEE intelligent transportation systems (ITSC), pp 312–317

  4. Candia J, González MC, Wang P, Schoenharl T, Madey G, Barabási A-L (2008) Uncovering individual and collective human dynamics from mobile phone records. J Phys A Math Theor 41(22):224015

    Article  MathSciNet  Google Scholar 

  5. Cheng J, Adamic L, Dow PA, Kleinberg, JM, Leskovec J (2014) Can cascades be predicted? pp 925–936

  6. Cohen R, Havlin S, Ben-Avraham D (2002) Efficient immunization strategies for computer networks and populations. Phys Rev Lett 91(24):247901

    Article  Google Scholar 

  7. Crane R, Sornette D (2008) Robust dynamic classes revealed by measuring the response function of a social system. Proc Natl Acad Sci U S A 105(41):15649–53

    Article  Google Scholar 

  8. Cui P, Jin S, Yu L, Wang F, Zhu W, Yang S (2013) Cascading outbreak prediction in networks:a data-driven approach. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 901–909

  9. Dempster AP, Laird NM, Rubin DB (1977) Maximum likelihood from incomplete data via the EM algorithm. J Roy Stat Soc 39(1):1–38

    MathSciNet  MATH  Google Scholar 

  10. Galuba W, Aberer K, Chakraborty D, Despotovic Z, Kellerer W (2010) Outtweeting the twitterers-predicting information cascades in microblogs. WOSN 10:3–11

    Google Scholar 

  11. Harris TE (1963) THE theory of branching processes. Springer, Berlin, pp 5–46

    Book  Google Scholar 

  12. Iwata, T, Shah A, Ghahramani Z (2013) Discovering latent influence in online social activities via shared cascade poisson processes. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 266–274

  13. Kobayashi R, Lambiotte R (2016) TiDeH: Time-dependent hawkes process for predicting retweet dynamics

  14. Lehmann J, Gonçalves B, Ramasco JJ, Cattuto C (2011) Dynamical classes of collective attention in twitter. Comput Sci, 251–260

  15. Li C, Te L, Yu J, Yeh MY (2017) Forecasting participants of information diffusion on social networks with its applications. Inf Sci 422:432–446

    Article  Google Scholar 

  16. Lu Y, Yu L, Zhang T, Zang C, Cui P, Song C, Zhu W (2018) Collective human behavior in cascading system: discovery, modeling and applications. In: IEEE international conference on data mining

  17. Mcgrew WC (1998) Culture in nonhuman primates? Annu Rev Anthropol 27(1):301–328

    Article  Google Scholar 

  18. Mishra S, Rizoiu MA, Xie L (2016) Feature driven and point process approaches for popularity prediction. In: ACM international on conference on information and knowledge management, pp 1069–1078

  19. Moore C, Newman MEJ (2000) Epidemics and percolation in small-world networks. Phys Revi E Stat Phys Plasmas Fluids Relat Interdiscip Top 61(5):5678

    Google Scholar 

  20. Myers SA, Leskovec J (2010) On the convexity of latent social network inference

  21. R Dean M, Stouffer DB, Motter AE, Amaral LAN (2008) A Poissonian explanation for heavy tails in e-mail communication. Proc Nat Acad Sci USA 105(47):18153–18158

    Article  Google Scholar 

  22. Rodriguez MG, Balduzzi D, Schölkopf B (2011) Uncovering the temporal dynamics of diffusion networks, pp 561–568

  23. Rodriguez MG, Leskovec J, Schölkopf B (2013) Modeling information propagation with survival theory. In: International conference on machine learning, pp 666–674

  24. Rouvray DH (2002) The rich legacy of half a century of the wiener index. Elsevier Ltd, Amsterdam, pp 16–37

    Google Scholar 

  25. Sastry N, Yoneki E, Crowcroft J (2009) Buzztraq: predicting geographical access patterns of social cascades using social networks. In: ACM Eurosys Sns Workshop, pp 39–45

  26. Shen HW, Wang D, Song C, Barabási A (2014) Modeling and predicting popularity dynamics via reinforced Poisson processes. In: Twenty-eighth AAAI conference on artificial intelligence, pp 291–297

  27. Tang L, Liu H (2009) Scalable learning of collective behavior based on sparse social dimensions. In: ACM conference on information and knowledge management, pp 1107–1116

  28. Turner RH, Killian LM et al (1957) Collective behavior. Prentice-Hall, Englewood Cliffs

    Google Scholar 

  29. Yu L, Cui P, Song C, Zhang T, Yang S (2017) A temporally heterogeneous survival framework with application to social behavior dynamics. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining. ACM, pp 1295–1304

  30. Yu L, Cui P, Wang F, Song C, Yang S (2015) From micro to macro: uncovering and predicting information cascading process with behavioral dynamics. In: IEEE international conference on data mining, pp 559–568

  31. Yu L, Cui P, Wang F, Song C, Yang S (2017) Uncovering and predicting the dynamic process of information cascades with survival model. Knowl Inf Syst 50(2):1–27

    Article  Google Scholar 

  32. Zang C, Cui, P, Song C, Faloutsos C, Zhu W (2017) Quantifying structural patterns of information cascades. In: International conference on world wide web companion, pp 867–868

  33. Zhang Q, Gong Y, Guo Y, Huang X (2015) Twenty-ninth AAAI conference on artificial intelligence, pp 403–409

  34. Zhao Q, Erdogdu MA, He HY, Rajaraman A, Leskovec J (2015) SEISMIC: a self-exciting point process model for predicting tweet popularity. In: ACM SIGKDD international conference on knowledge discovery and data mining, pp 1513–1522

Download references

Acknowledgements

The authors thank anonymous reviewers for many useful discussions and insightful suggestions. This work was supported in part by National Key R&D Program of China (No. 2018AAA0102004), National Natural Science Foundation of China (Nos. U1936219, 61772304, 61531006, U1611461), Beijing Academy of Artificial Intelligence (BAAI ), and a grant from the Institute for Guo Qiang, Tsinghua University. Thanks for the research fund of Tsinghua-Tencent Joint Laboratory for Internet Innovation Technology and the Young Elite Scientist Sponsorship Program by CAST. Song was partly supported by the National Science Foundation (IBSS-L-1620294). Wenwu Zhu is the corresponding author. All opinions, findings, and conclusions in this paper are those of the authors and do not necessarily reflect the views of the funding agencies.

Author information

Authors and Affiliations

  1. Department of Computer Science and Technology, Tsinghua University, Beijing, 100084, China

    Yunfei Lu, Linyun Yu, Tianyang Zhang, Chengxi Zang, Peng Cui & Wenwu Zhu

  2. Department of Physics, University of Miami, Coral Gables, FL, USA

    Chaoming Song

Authors
  1. Yunfei Lu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Linyun Yu
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Tianyang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chengxi Zang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Peng Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Chaoming Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Wenwu Zhu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Yunfei Lu.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lu, Y., Yu, L., Zhang, T. et al. Exploring the collective human behavior in cascading systems: a comprehensive framework. Knowl Inf Syst 62, 4599–4623 (2020). https://doi.org/10.1007/s10115-020-01506-8

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10115-020-01506-8

Keywords

Search

Navigation