End-to-End Influence Maximization in the Field

This paper presents the CHANGE agent for influence maximization, a multiagent problem with many applications in preventative health and other domains. CHANGE addresses major barriers to the deployment of influence maximization by service providers through a series of algorithmic contributions, backed by simulation results on real-world networks. We then conducted a real-world pilot study of CHANGE with a drop-in center serving homeless youth, the first such pilot study of sampling-based influence maximization and only the second study testing any influence maximization agent in the real world. CHANGE obtained comparable influence spread to previously field tested algorithms, but surveyed only 18% of youth to obtain network data. CHANGE has empirical promise in delivering high-quality influence maximization solutions in a manner which can be feasibly implemented by a service provider. While the algorithms underlying CHANGE are easy to implement, they draw on a series of insights into the social behavior of homeless youth. One lesson learned from our study is that, to be successful in the field, algorithms must be designed with their target population and setting in mind. CHANGE both navigates challenges specific to homeless youth (e.g., the difficulty of locating youth to query for edges or serve as peer leaders) and leverages properties of their social network (the friendship paradox). Our experience shows that accounting for both challenges and opportunities in the target population is crucial to produce a practically deployable algorithm.

[1]  Lars Backstrom,et al.  The Anatomy of the Facebook Social Graph , 2011, ArXiv.

[2]  Xiaokui Xiao,et al.  Influence maximization: near-optimal time complexity meets practical efficiency , 2014, SIGMOD Conference.

[3]  Ariel D. Procaccia,et al.  Dynamic Influence Maximization Under Increasing Returns to Scale , 2015, AAMAS.

[4]  Edith Cohen,et al.  Sketch-based Influence Maximization and Computation: Scaling up with Guarantees , 2014, CIKM.

[5]  N. Milburn,et al.  Pro-social and problematic social network influences on HIV/AIDS risk behaviours among newly homeless youth in Los Angeles , 2007, AIDS care.

[6]  Y. Narahari,et al.  Incentive compatible influence maximization in social networks and application to viral marketing , 2011, AAMAS.

[7]  Scott D. Gest,et al.  Identifying Children's Peer Social Networks in School Classrooms: Links Between Peer Reports and Observed Interactions , 2003 .

[8]  Nicole Immorlica,et al.  Uncharted but not Uninfluenced: Influence Maximization with an Uncertain Network , 2017, AAMAS.

[9]  Milind Tambe,et al.  Towards Robust Multi-objective Optimization Under Model Uncertainty for Energy Conservation , 2012 .

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

[11]  T. Valente,et al.  Peers, schools, and adolescent cigarette smoking. , 2001, The Journal of adolescent health : official publication of the Society for Adolescent Medicine.

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

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

[14]  S. Feld.  Why Your Friends Have More Friends Than You Do , 1991, American Journal of Sociology.

[15]  Laks V. S. Lakshmanan,et al.  SIMPATH: An Efficient Algorithm for Influence Maximization under the Linear Threshold Model , 2011, 2011 IEEE 11th International Conference on Data Mining.

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

[17]  Wei Chen,et al.  Scalable influence maximization for prevalent viral marketing in large-scale social networks , 2010, KDD.

[18]  T. Valente,et al.  Identifying Opinion Leaders to Promote Behavior Change , 2007, Health education & behavior : the official publication of the Society for Public Health Education.

[19]  Minjie Zhang,et al.  Agent-based Influence Maintenance in Social Networks , 2017, AAMAS.

[20]  Kristina Lerman,et al.  Friendship Paradox Redux: Your Friends Are More Interesting Than You , 2013, ICWSM.

[21]  David Kempe,et al.  Robust Influence Maximization , 2016, KDD.

[22]  Kyomin Jung,et al.  IRIE: Scalable and Robust Influence Maximization in Social Networks , 2011, 2012 IEEE 12th International Conference on Data Mining.

[23]  N. Milburn,et al.  Mobilizing homeless youth for HIV prevention: a social network analysis of the acceptability of a face-to-face and online social networking intervention. , 2012, Health education research.

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

[25]  Nicole Immorlica,et al.  Maximizing Influence in an Unknown Social Network , 2018, AAAI.

[26]  Pradeep Varakantham,et al.  Robust influence Maximization , 2016 .

[27]  Haifeng Xu,et al.  Using Social Networks to Aid Homeless Shelters: Dynamic Influence Maximization under Uncertainty , 2016, AAMAS.

[28]  Laks V. S. Lakshmanan,et al.  CELF++: optimizing the greedy algorithm for influence maximization in social networks , 2011, WWW.

[29]  Eric Rice,et al.  Online Social Networking Technologies, HIV Knowledge, and Sexual Risk and Testing Behaviors Among Homeless Youth , 2010, AIDS and Behavior.