Influence Maximization for Social Good: Use of Social Networks in Low Resource Communities

This thesis proposal makes the following technical contributions: (i) we provide a definition of the Dynamic Influence Maximization Under Uncertainty (or DIME) problem, which models the problem faced by homeless shelters accurately; (ii) we propose a novel Partially Observable Markov Decision Process (POMDP) model for solving the DIME problem; (iii) we design two scalable POMDP algorithms (PSINET and HEALER) for solving the DIME problem, since conventional POMDP solvers fail to scale up to sizes of interest; and (iv) we test our algorithms effectiveness in the real world by conducting a pilot study with actual homeless youth in Los Angeles. The success of this pilot (as explained later) shows the promise of using influence maximization for social good on a larger scale.

[1]  Brahim Chaib-draa,et al.  An online POMDP algorithm for complex multiagent environments , 2005, AAMAS '05.

[2]  Martin L. Puterman,et al.  Markov Decision Processes: Discrete Stochastic Dynamic Programming , 1994 .

[3]  Joel Veness,et al.  Monte-Carlo Planning in Large POMDPs , 2010, NIPS.

[4]  Leandro Soriano Marcolino,et al.  Preventing HIV Spread in Homeless Populations Using PSINET , 2015, AAAI.

[5]  Camille Roth,et al.  How Realistic Should Knowledge Diffusion Models Be? , 2007, J. Artif. Soc. Soc. Simul..

[6]  Eric Rice,et al.  Maximizing Awareness about HIV in Social Networks of Homeless Youth with Limited Information , 2017, IJCAI.

[7]  Milind Tambe,et al.  Bridging the Gap Between Theory and Practice in Influence Maximization: Raising Awareness about HIV among Homeless Youth , 2018, IJCAI.

[8]  Allan Borodin,et al.  Threshold Models for Competitive Influence in Social Networks , 2010, WINE.

[9]  Nicholas Mattei,et al.  An English-Language Argumentation Interface for Explanation Generation with Markov Decision Processes in the Domain of Academic Advising , 2013, TIIS.

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

[11]  Leandro Soriano Marcolino,et al.  Please be an Influencer?: Contingency-Aware Influence Maximization , 2018, AAMAS.

[12]  Eric Rice,et al.  POMDPs for Assisting Homeless Shelters - Computational and Deployment Challenges , 2016, AAMAS Workshops.

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

[14]  Jean-Charles Pomerol,et al.  Multicriterion Decision in Management: Principles and Practice , 2012 .

[15]  Shishir Bharathi,et al.  Competitive Influence Maximization in Social Networks , 2007, WINE.

[16]  Milind Tambe,et al.  Piloting the Use of Artificial Intelligence to Enhance HIV Prevention Interventions for Youth Experiencing Homelessness , 2018, Journal of the Society for Social Work and Research.

[17]  Paul R. Cohen,et al.  Influence Propagation in Modular Networks , 2008, AAAI Spring Symposium: Social Information Processing.

[18]  Paul R. Cohen,et al.  Maximizing Influence Propagation in Networks with Community Structure , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

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

[20]  Milind Tambe,et al.  Explanation Systems for Influence Maximization Algorithms , 2017, SocInf@IJCAI.

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

[22]  Andreas Krause,et al.  Adaptive Submodularity: Theory and Applications in Active Learning and Stochastic Optimization , 2010, J. Artif. Intell. Res..

[23]  Aram Galstyan,et al.  Information-theoretic measures of influence based on content dynamics , 2012, WSDM.

[24]  Masahiro Kimura,et al.  Tractable Models for Information Diffusion in Social Networks , 2006, PKDD.

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

[26]  Kristina Lerman,et al.  The "Majority Illusion" in Social Networks , 2015, PloS one.

[27]  Roger Wattenhofer,et al.  Word of Mouth: Rumor Dissemination in Social Networks , 2008, SIROCCO.

[28]  Kristina Lerman,et al.  Community Detection Using a Measure of Global Influence , 2008, SNAKDD.

[29]  Kristina Lerman,et al.  Leaders and Negotiators: An Influence-based Metric for Rank , 2009, ICWSM.

[30]  George Karypis,et al.  Multi-threaded Graph Partitioning , 2013, 2013 IEEE 27th International Symposium on Parallel and Distributed Processing.

[31]  Leandro Soriano Marcolino,et al.  PSINET: Assisting HIV Prevention Amongst Homeless Youth by Planning Ahead , 2016, AI Mag..

[32]  Dongqing Yang,et al.  Influence Maximizing and Local Influenced Community Detection Based on Multiple Spread Model , 2011, ADMA.

[33]  E. Rice.  The Positive Role of Social Networks and Social Networking Technology in the Condom-Using Behaviors of Homeless Young People , 2010, Public health reports.

[34]  E. Rice,et al.  Sexuality and homelessness in Los Angeles public schools. , 2012, American journal of public health.

[35]  Tamara G. Kolda,et al.  Community structure and scale-free collections of Erdös-Rényi graphs , 2011, Physical review. E, Statistical, nonlinear, and soft matter physics.

[36]  Eric Rice,et al.  Using social networks to raise HIV awareness among homeless youth , 2017, IBM J. Res. Dev..

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

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

[39]  Leandro Soriano Marcolino,et al.  Diverse Randomized Agents Vote to Win , 2014, NIPS.

[40]  Thien Hai Nguyen,et al.  Handling Payoff Uncertainty with Adversary Bounded Rationality in Green Security Domains , 2015 .

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

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

[43]  Judith Masthoff,et al.  A Survey of Explanations in Recommender Systems , 2007, 2007 IEEE 23rd International Conference on Data Engineering Workshop.

[44]  Pascal Poupart,et al.  Minimal Sufficient Explanations for Factored Markov Decision Processes , 2009, ICAPS.

[45]  Christian Borgs,et al.  Maximizing Social Influence in Nearly Optimal Time , 2012, SODA.

[46]  Leen-Kiat Soh,et al.  To Ask, Sense, or Share: Ad Hoc Information Gathering , 2015, AAMAS.