How Iranian Instagram users act for parliament election campaign? A study based on followee network

Social media place where people communicate and share their ideas provide rich information for social network analysis. There are various analyses such as information diffusion modeling and community detection which are used to analyze data of social networks. In this paper, we investigate some novel aspects of hashtag diffusion among Iranian communities in Instagram in the period of the last legislative election in Iran. After data preparation, we analyze the validation of three different assumptions. First, we study the effects of follower-followee relations in the spread of the campaign hashtags. Based on the timestamps of the posts, we invoke NetRate method to estimate information diffusion rates over edges of follower-followee network. Then, by application of Louvain method as a community detection algorithm, we investigate the relation of community membership and contagion transmission rate. Finally, we study observed topical preferences in network communities. Results show the flow of information from followees to followers with a significant rate of diffusion over the whole network. However, being part of a specific community does not contribute to be exposed to a cascade faster than others. While the communities were defined based on modularity maximization and no information related to hashtags involved, a topical preference also is observed within the communities' hashtags which had the same orientation as observed in two major political parties of Iran.

[1]  M E J Newman,et al.  Fast algorithm for detecting community structure in networks. , 2003, Physical review. E, Statistical, nonlinear, and soft matter physics.

[2]  M. Newman,et al.  Finding community structure in very large networks. , 2004, Physical review. E, Statistical, nonlinear, and soft matter physics.

[3]  Matthieu Latapy,et al.  Computing Communities in Large Networks Using Random Walks , 2004, J. Graph Algorithms Appl..

[4]  Ken Wakita,et al.  Finding community structure in mega-scale social networks: [extended abstract] , 2007, WWW '07.

[5]  Jean-Loup Guillaume,et al.  Fast unfolding of communities in large networks , 2008, 0803.0476.

[6]  Santo Fortunato,et al.  Community detection in graphs , 2009, ArXiv.

[7]  Jure Leskovec,et al.  On the Convexity of Latent Social Network Inference , 2010, NIPS.

[8]  Scott Counts,et al.  Predicting the Speed, Scale, and Range of Information Diffusion in Twitter , 2010, ICWSM.

[9]  Jon Kleinberg,et al.  Differences in the mechanics of information diffusion across topics: idioms, political hashtags, and complex contagion on twitter , 2011, WWW.

[10]  Bernhard Scholkopf,et al.  Submodular Inference of Diffusion Networks from Multiple Trees , 2012, ICML.

[11]  Jure Leskovec,et al.  Inferring networks of diffusion and influence , 2010, KDD.

[12]  Cécile Favre,et al.  Information diffusion in online social networks: a survey , 2013, SGMD.

[13]  R. Lambiotte,et al.  Multilevel Local Optimization of Modularity , 2013 .

[14]  Bernhard Schölkopf,et al.  Uncovering the structure and temporal dynamics of information propagation , 2014, Network Science.

[15]  Jure Leskovec,et al.  Can cascades be predicted? , 2014, WWW.

[16]  Andrea Tagarelli,et al.  Online popularity and topical interests through the lens of instagram , 2014, HT.

[17]  Alan Kai-Hau Yeung,et al.  Similarity between community structures of different online social networks and its impact on underlying community detection , 2015, Commun. Nonlinear Sci. Numer. Simul..

[18]  Hongyuan Zha,et al.  Back to the Past: Source Identification in Diffusion Networks from Partially Observed Cascades , 2015, AISTATS.

[19]  Georgina Kennedy,et al.  Characterizing Twitter Discussions About HPV Vaccines Using Topic Modeling and Community Detection , 2016, Journal of medical Internet research.