Social Network Based Substance Abuse Prevention via Network Modification (A Preliminary Study)

Substance use and abuse is a significant public health problem in the United States. Group-based intervention programs offer a promising means of preventing and reducing substance abuse. While effective, unfortunately, inappropriate intervention groups can result in an increase in deviant behaviors among participants, a process known as deviancy training. This paper investigates the problem of optimizing the social influence related to the deviant behavior via careful construction of the intervention groups. We propose a Mixed Integer Optimization formulation that decides on the intervention groups, captures the impact of the groups on the structure of the social network, and models the impact of these changes on behavior propagation. In addition, we propose a scalable hybrid meta-heuristic algorithm that combines Mixed Integer Programming and Large Neighborhood Search to find near-optimal network partitions. Our algorithm is packaged in the form of GUIDE, an AI-based decision aid that recommends intervention groups. Being the first quantitative decision aid of this kind, GUIDE is able to assist practitioners, in particular social workers, in three key areas: (a) GUIDE proposes near-optimal solutions that are shown, via extensive simulations, to significantly improve over the traditional qualitative practices for forming intervention groups; (b) GUIDE is able to identify circumstances when an intervention will lead to deviancy training, thus saving time, money, and effort; (c) GUIDE can evaluate current strategies of group formation and discard strategies that will lead to deviancy training. In developing GUIDE, we are primarily interested in substance use interventions among homeless youth as a high risk and vulnerable population. GUIDE is developed in collaboration with Urban Peak, a homeless-youth serving organization in Denver, CO, and is under preparation for deployment.

[1]  Dylan Walker,et al.  Tie Strength, Embeddedness, and Social Influence: A Large-Scale Networked Experiment , 2014, Manag. Sci..

[2]  M. Macy,et al.  Complex Contagions and the Weakness of Long Ties1 , 2007, American Journal of Sociology.

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

[4]  Ariel D. Procaccia,et al.  Optimizing kidney exchange with transplant chains: theory and reality , 2012, AAMAS.

[5]  J. Kelly,et al.  The Evolutionary Significance of Affect in Groups: Communication and Group Bonding , 2004 .

[6]  Dorothea Wagner,et al.  Dynamic Graph Clustering Using Minimum-Cut Trees , 2009, J. Graph Algorithms Appl..

[7]  Adeline Nyamathi,et al.  Characteristics of homeless youth who use cocaine and methamphetamine. , 2012, The American journal on addictions.

[8]  Anthony Wirth,et al.  Correlation Clustering , 2010, Encyclopedia of Machine Learning and Data Mining.

[9]  Milind Tambe,et al.  A Robust Optimization Approach to Designing Near-Optimal Strategies for Constant-Sum Monitoring Games , 2018, GameSec.

[10]  C W Dent,et al.  One-year outcomes of Project Towards No Drug Abuse. , 1998, Preventive medicine.

[11]  Brady T West,et al.  Social contexts of substance use among U.S. high school seniors: a multicohort national study. , 2014, The Journal of adolescent health : official publication of the Society for Adolescent Medicine.

[12]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

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

[14]  Deborah M Caldwell,et al.  Peer‐led interventions to prevent tobacco, alcohol and/or drug use among young people aged 11–21 years: a systematic review and meta‐analysis , 2016 .

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

[16]  Le Song,et al.  Scalable diffusion-aware optimization of network topology , 2014, KDD.

[17]  Paul Shaw,et al.  Using Constraint Programming and Local Search Methods to Solve Vehicle Routing Problems , 1998, CP.

[18]  Thomas W Valente,et al.  Effects of a social-network method for group assignment strategies on peer-led tobacco prevention programs in schools. , 2003, American journal of public health.

[19]  Masahiro Kimura,et al.  Solving the Contamination Minimization Problem on Networks for the Linear Threshold Model , 2008, PRICAI.

[20]  Russell Bent,et al.  Large Neighborhood Search for Energy Aware Meeting Scheduling in Smart Buildings , 2015, CPAIOR.

[21]  Hickman Matthew,et al.  Peer‐led interventions to prevent tobacco, alcohol and/or drug use among young people aged 11–21 years: a systematic review and meta‐analysis , 2016, Addiction.