Maximizing Awareness about HIV in Social Networks of Homeless Youth with Limited Information

This paper presents HEALER, a software agent that recommends sequential intervention plans for use by homeless shelters, who organize these interventions to raise awareness about HIV among homeless youth. HEALER’s sequential plans (built using knowledge of social networks of homeless youth) choose intervention participants strategically to maximize influence spread, while reasoning about uncertainties in the network. While previous work presents influence maximizing techniques to choose intervention participants, they do not address two real-world issues: (i) they completely fail to scale up to real-world sizes; and (ii) they do not handle deviations in execution of intervention plans. HEALER handles these issues via two major contributions: (i) HEALER casts this influence maximization problem as a POMDP and solves it using a novel planner which scales up to previously unsolvable real-world sizes; and (ii) HEALER allows shelter officials to modify its recommendations, and updates its future plans in a deviationtolerant manner. HEALER was deployed in the real world in Spring 2016 with considerable success.

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

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

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

[4]  Vol XXVmI,et al.  Public Health Reports , 1941, The Indian medical gazette.

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

[6]  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.

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

[8]  Sa Azin,et al.  An overview on the 2008 UNAIDS Report on the 2008 UNAIDS Report on the Global AIDS Epidemic. , 2010 .

[9]  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.

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

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

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

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

[14]  Michael I. Jordan,et al.  Advances in Neural Information Processing Systems 30 , 1995 .

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

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

[17]  Vandana Sundaram,et al.  The American Journal of Public Health. , 1945, American journal of public health and the nation's health.

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

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