Identification of influential users on Twitter: A novel weighted correlated influence measure for Covid-19

Abstract In the era of advanced mobile technology, freedom of expression over social media has become prevalent among online users. This generates a huge amount of communication that eventually forms a ground for extensive research and analysis. The social network analysis allows identifying the influential people in society over microblogging platforms. Twitter, being an evolving social media platform, has become increasingly vital for online dialogues, trends, and content virality. Applications of discovering influential users over Twitter are manifold. It includes viral marketing, brand analysis, news dissemination, health awareness spreading, propagating political movement, and opinion leaders for empowering governance. In our research, we have proposed a sustainable approach, namely Weighted Correlated Influence (WCI), which incorporates the relative impact of timeline-based and trend-specific features of online users. Our methodology considers merging the profile activity and underlying network topology to designate online users with an influence score, which represents the combined effect. To quantify the performance of our proposed method, the Twitter trend #CoronavirusPandemic is used. Also, the results are validated for another social media trend. The experimental outcomes depict enhanced performance of proposed WCI over existing methods that are based on precision, recall, and F1-measure for validation.

[1]  Ruth Nussinov,et al.  Structure and dynamics of molecular networks: A novel paradigm of drug discovery. A comprehensive review , 2012, Pharmacology & therapeutics.

[2]  Scott Counts,et al.  Identifying topical authorities in microblogs , 2011, WSDM '11.

[3]  Jia Yan,et al.  Mining topical influencers based on the multi-relational network in micro-blogging sites , 2013, China Communications.

[4]  Daniel M. Romero,et al.  Influence and passivity in social media , 2010, ECML/PKDD.

[5]  Phillip Bonacich,et al.  Eigenvector-like measures of centrality for asymmetric relations , 2001, Soc. Networks.

[6]  Beng Chin Ooi,et al.  TI: an efficient indexing mechanism for real-time search on tweets , 2011, SIGMOD '11.

[7]  Masoud Rahgozar,et al.  OLFinder: Finding opinion leaders in online social networks , 2016, J. Inf. Sci..

[8]  Yamir Moreno,et al.  The Dynamics of Protest Recruitment through an Online Network , 2011, Scientific reports.

[9]  Cathy C Sarli,et al.  Measuring academic productivity and changing definitions of scientific impact. , 2014, Missouri medicine.

[10]  P. Bonacich.  Power and Centrality: A Family of Measures , 1987, American Journal of Sociology.

[11]  Feng Xiao,et al.  Twitter User Rank Using Keyword Search , 2012, European-Japanese Conference on Information Modelling and Knowledge Bases.

[12]  Mohamed Bouguessa,et al.  Identifying Authorities in Online Communities , 2015, ACM Trans. Intell. Syst. Technol..

[13]  Virgílio A. F. Almeida,et al.  Sentiment-based influence detection on Twitter , 2011, Journal of the Brazilian Computer Society.

[14]  Mohand Boughanem,et al.  Active Microbloggers: Identifying Influencers, Leaders and Discussers in Microblogging Networks , 2012, SPIRE.

[15]  Barbara K. Kaye,et al.  The tweet goes on: Interconnection of Twitter opinion leadership, network size, and civic engagement , 2017, Comput. Hum. Behav..

[16]  Sule Gündüz Ögüdücü,et al.  Identifying topical influencers on twitter based on user behavior and network topology , 2018, Knowl. Based Syst..

[17]  Prasanna Gai,et al.  Contagion in financial networks , 2010, Proceedings of the Royal Society A: Mathematical, Physical and Engineering Sciences.

[18]  Aimin Jiang,et al.  Identification and role of opinion leaders in information diffusion for online discussion network , 2020, J. Ambient Intell. Humaniz. Comput..

[19]  Les Carr,et al.  Identifying communicator roles in twitter , 2012, WWW.

[20]  Wei Xu,et al.  ACQR: A Novel Framework to Identify and Predict Influential Users in Micro-Blogging , 2013, PACIS.

[21]  Nishanth R. Sastry,et al.  IARank: Ranking Users on Twitter in Near Real-Time, Based on Their Information Amplification Potential , 2012, 2012 International Conference on Social Informatics.

[22]  S. Stigler.  Francis Galton's Account of the Invention of Correlation , 1989 .

[23]  Daniel Gayo-Avello,et al.  Nepotistic relationships in Twitter and their impact on rank prestige algorithms , 2010, Inf. Process. Manag..

[24]  U. Brandes.  A faster algorithm for betweenness centrality , 2001 .

[25]  Freimut Bodendorf,et al.  Detecting opinion leaders and trends in online social networks , 2009, CIKM-SWSM.

[26]  Krishna P. Gummadi,et al.  Measuring User Influence in Twitter: The Million Follower Fallacy , 2010, ICWSM.

[27]  Ling Feng,et al.  A Tweet-Centric Approach for Topic-Specific Author Ranking in Micro-Blog , 2011, ADMA.

[28]  C. A. Murthy,et al.  A New Centrality Measure for Influence Maximization in Social Networks , 2011, PReMI.

[29]  Leonard M. Freeman,et al.  A set of measures of centrality based upon betweenness , 1977 .

[30]  Martine De Cock,et al.  Ranking Approaches for Microblog Search , 2010, 2010 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology.

[31]  Mohsen Guizani,et al.  Discovering influential users in micro-blog marketing with influence maximization mechanism , 2012, 2012 IEEE Global Communications Conference (GLOBECOM).

[32]  Hosung Park,et al.  What is Twitter, a social network or a news media? , 2010, WWW '10.