Anticipating Activity in Social Media Spikes

We propose a novel mathematical model for the activity of microbloggers during an external, event-driven spike. The model leads to a testable prediction of who would become most active if a spike were to take place. This type of information is of great interest to commercial organisations, governments and charities, as it identifies key players who can be targeted with information in real time when the network is most receptive. The model takes account of the fact that dynamic interactions evolve over an underlying, static network that records who listens to whom. The model is based on the assumption that, in the case where the entire community has become aware of an external news event, a key driver of activity is the motivation to participate by responding to incoming messages. We test the model on a large scale Twitter conversation concerning the appointment of a UK Premier League football club manager. We also present further results for a Bundesliga football match, a marketing event and a television programme. In each case we find that exploiting the underlying connectivity structure improves the prediction of who will be active during a spike. We also show how the half-life of a spike in activity can be quantified in terms of the network size and the typical response rate.

[1]  Alexander V. Mantzaris,et al.  Discovering and validating influence in a dynamic online social network , 2013, Social Network Analysis and Mining.

[2]  Gene H. Golub,et al.  Matrix computations , 1983 .

[3]  Sinan Aral,et al.  Social science: Poked to vote , 2012, Nature.

[4]  Sinan Aral,et al.  Identifying Influential and Susceptible Members of Social Networks , 2012, Science.

[5]  David Lazer,et al.  Rising Tides or Rising Stars?: Dynamics of Shared Attention on Twitter during Media Events , 2013, PloS one.

[6]  Lada A. Adamic,et al.  The role of social networks in information diffusion , 2012, WWW.

[7]  Mark Newman,et al.  Networks: An Introduction , 2010 .

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

[9]  James P. Gleeson,et al.  Competition-induced criticality in a model of meme popularity , 2013, Physical review letters.

[10]  Duncan J. Watts,et al.  Everyone's an influencer: quantifying influence on twitter , 2011, WSDM '11.

[11]  Kristina Lerman,et al.  Social Contagion: An Empirical Study of Information Spread on Digg and Twitter Follower Graphs , 2012, ArXiv.

[12]  Lada A. Adamic,et al.  Computational Social Science , 2009, Science.

[13]  Ciro Cattuto,et al.  Dynamical classes of collective attention in twitter , 2011, WWW.

[14]  Yamir Moreno,et al.  Cascading behaviour in complex socio-technical networks , 2013, J. Complex Networks.

[15]  Karen Rose,et al.  What is Twitter , 2009 .

[16]  Muhammad Zubair Shafiq,et al.  Modeling Morphology of Social Network Cascades , 2013, ArXiv.

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

[18]  Jure Leskovec,et al.  The dynamics of viral marketing , 2005, EC '06.

[19]  Rizal Setya Perdana.  What is Twitter , 2013 .

[20]  Nicholas J. Higham,et al.  Functions of matrices - theory and computation , 2008 .

[21]  Leo Katz,et al.  A new status index derived from sociometric analysis , 1953 .

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

[23]  Damon Centola,et al.  The Spread of Behavior in an Online Social Network Experiment , 2010, Science.

[24]  Duncan J. Watts,et al.  Who says what to whom on twitter , 2011, WWW.

[25]  Alessandro Vespignani,et al.  Beating the news using social media: the case study of American Idol , 2012, EPJ Data Science.

[26]  Joachim Mathiesen,et al.  Excitable human dynamics driven by extrinsic events in massive communities , 2013, Proceedings of the National Academy of Sciences.