Activating the "Breakfast Club": Modeling Influence Spread in Natural-World Social Networks

While reigning models of diffusion have privileged the structure of a given social network as the key to informational exchange, real human interactions do not appear to take place on a single graph of connections. Using data collected from a pilot study of the spread of HIV awareness in social networks of homeless youth, we show that health information did not diffuse in the field according to the processes outlined by dominant models. Since physical network diffusion scenarios often diverge from their more well-studied counterparts on digital networks, we propose an alternative Activation Jump Model (AJM) that describes information diffusion on physical networks from a multi-agent team perspective. Our model exhibits two main differentiating features from leading cascade and threshold models of influence spread: 1) The structural composition of a seed set team impacts each individual node's influencing behavior, and 2) an influencing node may spread information to non-neighbors. We show that the AJM significantly outperforms existing models in its fit to the observed node-level influence data on the youth networks. We then prove theoretical results, showing that the AJM exhibits many well-behaved properties shared by dominant models. Our results suggest that the AJM presents a flexible and more accurate model of network diffusion that may better inform influence maximization in the field.

[1]  T. Valente Network Interventions , 2012, Science.

[2]  Mark S. Granovetter The Strength of Weak Ties , 1973, American Journal of Sociology.

[3]  T. Schelling Micromotives and Macrobehavior , 1978 .

[4]  Devon D. Brewer,et al.  Forgetting in the recall-based elicitation of personal and social networks , 2000, Soc. Networks.

[5]  Tom Fawcett,et al.  An introduction to ROC analysis , 2006, Pattern Recognit. Lett..

[6]  S. Friedman,et al.  Some Data-Driven Reflections on Priorities in AIDS Network Research , 2007, AIDS and Behavior.

[7]  Le Song,et al.  Learning Triggering Kernels for Multi-dimensional Hawkes Processes , 2013, ICML.

[8]  Carter T. Butts,et al.  Network inference, error, and informant (in)accuracy: a Bayesian approach , 2003, Soc. Networks.

[9]  R J Mills,et al.  Harnessing peer networks as an instrument for AIDS prevention: results from a peer-driven intervention. , 1998, Public health reports.

[10]  Marie desJardins,et al.  Adapting Network Structure for Efficient Team Formation , 2004, AAAI Technical Report.

[11]  Tucker R. Balch,et al.  Hierarchic Social Entropy: An Information Theoretic Measure of Robot Group Diversity , 2000, Auton. Robots.

[13]  Amin Karbasi,et al.  Greed Is Good: Near-Optimal Submodular Maximization via Greedy Optimization , 2017, COLT.

[14]  Wei Chen,et al.  Efficient influence maximization in social networks , 2009, KDD.

[15]  Ron Kohavi,et al.  The Case against Accuracy Estimation for Comparing Induction Algorithms , 1998, ICML.

[16]  Arun G. Chandrasekhar,et al.  The Diffusion of Microfinance , 2012, Science.

[17]  Marie desJardins,et al.  Team Formation in Complex Networks , 2003 .

[18]  Sarit Kraus,et al.  The influence of social dependencies on decision-making: initial investigations with a new game , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[19]  Manuela M. Veloso,et al.  Modeling and learning synergy for team formation with heterogeneous agents , 2012, AAMAS.

[20]  Noa Agmon,et al.  Leading ad hoc agents in joint action settings with multiple teammates , 2012, AAMAS.

[21]  Ali A. Minai,et al.  Agents of influence in social networks , 2012, AAMAS.

[22]  Mark S. Granovetter Threshold Models of Collective Behavior , 1978, American Journal of Sociology.

[23]  Lu Hong,et al.  Groups of diverse problem solvers can outperform groups of high-ability problem solvers. , 2004, Proceedings of the National Academy of Sciences of the United States of America.

[24]  Milind Tambe,et al.  Influence Maximization in the Field: The Arduous Journey from Emerging to Deployed Application , 2017, AAMAS.

[25]  Leandro Soriano Marcolino,et al.  Multi-Agent Team Formation: Diversity Beats Strength? , 2013, IJCAI.

[26]  Gita Reese Sukthankar,et al.  Identifying influential agents for advertising in multi-agent markets , 2012, AAMAS.

[27]  Laks V. S. Lakshmanan,et al.  Learning influence probabilities in social networks , 2010, WSDM '10.

[28]  Andreas Krause,et al.  Cost-effective outbreak detection in networks , 2007, KDD '07.

[29]  J. Kalafat,et al.  An evaluation of a school-based suicide awareness intervention. , 1994, Suicide & life-threatening behavior.

[30]  Jure Leskovec,et al.  Information diffusion and external influence in networks , 2012, KDD.

[31]  Steven B. Andrews,et al.  Structural Holes: The Social Structure of Competition , 1995, The SAGE Encyclopedia of Research Design.

[32]  Laks V. S. Lakshmanan,et al.  A Data-Based Approach to Social Influence Maximization , 2011, Proc. VLDB Endow..

[33]  Xueqi Cheng,et al.  Learning User-Specific Latent Influence and Susceptibility from Information Cascades , 2013, AAAI.

[34]  Robert Liebendorfer Mind, self and society , 1960 .

[35]  Éva Tardos,et al.  Maximizing the Spread of Influence through a Social Network , 2015, Theory Comput..

[36]  Lars Backstrom,et al.  Structural diversity in social contagion , 2012, Proceedings of the National Academy of Sciences.

[37]  N. Milburn,et al.  Position-specific HIV risk in a large network of homeless youths. , 2012, American journal of public health.

[38]  D. Krackhardt,et al.  Whether close or far: Social distance effects on perceived balance in friendship networks , 1999 .

[39]  Termeh Shafie,et al.  A Multigraph Approach to Social Network Analysis , 2015, J. Soc. Struct..

[40]  Moshe Dor,et al.  אבן, and: Stone , 2017 .

[41]  M. Degroot Reaching a Consensus , 1974 .