A Method for Measuring Popularity of Popular Events in Social Networks Using Swarm Intelligence

  • Jiaying ChenEmail author
  • Zhenyu Wu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 905)


Social network is a platform for users to post and forward contents that they are paying attention to. So through the measurement of the popularity of the event, it is possible to excavate social focus and predict the development trend of the event. The user is used as the main body to measure the popularity, so as to construct the interaction graph, and the indicator of the graph has a degree distribution sequence, a clustering coefficient and a degree centrality. Among them, the user distribution of the degree distribution sequence of the interaction graph shows the distribution of “power law distribution”, and the power index introduced by the degree distribution sequence can effectively reflect the distribution of the user’s participation degree in the popular event; the clustering coefficient reflects the user’s agglomeration in the popular event; the degree centrality reflects the dominant position of the user participating in the popular event; the number of users reflects the size of the network formed by the popular event. The comprehensive indicator obtained after nondimensionalization and analytic hierarchy process of these four indicators can comprehensively and accurately measure the popularity of popular events. The comprehensive indicator shows that the popular event of the “Ching Ming Festival” is more consistent with the actual situation during the day. Further more, the measure of popularity is more sensitive and can reflect minor changes in the popular spot.


Interaction graph Event popularity Analytic hierarchy process 



This work is supported by Natural Science Foundation of China (No. 61502246), NUPTSF (No. NY215019).


  1. 1.
    Wang, S., Feng, L.X.: Mining chat text based on large data word identification of new hotspots opinion. Electron. Commer. 1, 60–61 (2018)Google Scholar
  2. 2.
    Lan, Y.X., Liu, B.Y., Zhang, P., Xia, Y.X., Li, Y.Q.: Research on dynamic prediction model of internet public opinion for big data. J. Inf. 36(06), 105–110+147 (2017)Google Scholar
  3. 3.
    Wang, Z.X.: Based on mining and emotional hot events microblogging analysis. Shanghai Jiaotong University (2013)Google Scholar
  4. 4.
    Gupta, A., Mittal, N., Kohli, N.: Analysis of a sporting event on a social network: true popularity & popularity bond. In: Proceedings of the International Conference on Data Engineering and Communication Technology. Springer, Singapore (2017)Google Scholar
  5. 5.
    Gupta, M., Gao, J., Zhai, C.X., Han, J.: Predicting future popularity trend of events in microblogging platforms. Proc. Assoc. Inf. Sci. Technol. 49(1), 1–10 (2012)CrossRefGoogle Scholar
  6. 6.
    Shen, P., Zhou, Y., Chen, K.: A probability based subnet selection method for hot event detection in Sina Weibo microblogging. In: IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, pp. 1410–1413 (2013)Google Scholar
  7. 7.
    Jia, R., Liu, T., Zhang, J., Fu, L.Y., Gan, X.Y., Wang, X.B.: Impact of content popularity on information coverage in online social networks. IEEE Trans. Veh. Technol. 99, 1 (2018)Google Scholar
  8. 8.
    Xu, Y.N.: Based on media spectacle heat network public opinion trends microblogging. Inf. Sci. 2, 92–97 (2017)Google Scholar
  9. 9.
    Li, H., Zhu, X.: Detection of emerging hot spots of Weibo based on influence. Comput. Appl. Softw. 33(05), 98–101+165 (2016)Google Scholar
  10. 10.
    Wang, C.N., Chen, W.Q., Xu, H.: Indicator System of microblogging public opinion monitoring and early warning of heat. Comput. Mod. 1, 126–129 (2013)Google Scholar
  11. 11.
    Lee, L.X., Yang, T.F.: Based on the government network Sina Weibo negative public opinion trend. J. Intell. 10, 97–100 (2015)Google Scholar
  12. 12.
    Yan, C.X., Zhang, X., Liu, L.: Based on the level of emergency response network public opinion Redu. China Manag. Sci. 22(3), 82–89 (2014)Google Scholar
  13. 13.
    Wen, L., Yao, Y.Y., Wang, C.K.: Research network public opinion Redu evaluation of food safety incidents: based on BP neural network method. Mod. Manag. Sci. 9, 30–32 (2016)Google Scholar
  14. 14.
    Sun, X,F., Cheng, S.H., Jin, X.T.: Government quantitative method for evaluating a negative public opinion of heat networks-Sina microblogging, for example. J. Intell. 8, 137–141 (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  1. 1.Institution of Internet of ThingsNanjing University of Posts and TelecommunicationsNanjingChina

Personalised recommendations