Understanding social influence using network analysis and machine learning
Author(s)Adjodah, Dhaval D. K. (Adjodlah, Dhaval Dhamnidhi Kumar)
Massachusetts Institute of Technology. Engineering Systems Division.
Alex S. Pentland.
MetadataShow full item record
If we are to enact better policy, fight crime and decrease poverty, we will need better computational models of how society works. In order to make computational social science a useful reality, we will need generative models of how social influence sprouts at the interpersonal level and how it leads to emergent social behavior. In this thesis, I take steps at understanding the predictors and conduits of social influence by analyzing real-life data, and I use the findings to create a high-accuracy prediction model of individuals' future behavior. The funf dataset which comprises detailed high-frequency data gathered from 25 mobile phone-based signals from 130 people over a period of 15 months, will be used to test the hypothesis that people who interact more with each other have a greater ability to influence each other. Various metrics of interaction will be investigated such as self-reported friendships, call and SMS logs and Bluetooth co-location signals. The Burt Network Constraint of each pair of participants is calculated as a measure of not only the direct interaction between two participants but also the indirect friendships through intermediate neighbors that form closed triads with both the participants being assessed. To measure influence, the results of the live funf intervention will be used where behavior change of each participant to be more physically active was rewarded, with the reward being calculated live. There were three variants of the reward structure: one where each participant was rewarded for her own behavior change without seeing that of anybody else (the control), one where each participant was paired up with two 'buddies' whose behavior change she could see live but she was still rewarded based on her own behavior, and one where each participant who was paired with two others was paid based on their behavior change that she could see live. As a metric for social influence, it will be considered how the change in slope and average physical activity levels of one person follows the change in slope and average physical activity levels of the buddy who saw her data and/or was rewarded based on her performance. Finally, a linear regression model that uses the various types of direction and indirect network interactions will be created to predict the behavior change of one participant based on her closeness with her buddy. In addition to explaining and demonstrating the causes of social influence with unprecedented detail using network analysis and machine learning, I will discuss the larger topic of using such a technology-driven approach to changing behavior instead of the traditional policy-driven approach. The advantages of the technology-driven approach will be highlighted and the potential political-economic pitfalls of implementing such a novel approach will also be addressed. Since technology-driven approaches to changing individual behavior can have serious negative consequences for democracy and the free-market, I will introduce a novel dimension to the discussion of how to protect individuals from the state and from powerful private organizations. Hence, I will describe how transparency policies and civic engagement technologies can further this goal of 'watching the watchers'.
Thesis (S.M. in Technology and Policy)--Massachusetts Institute of Technology, Engineering Systems Division, 2013.Cataloged from PDF version of thesis.Includes bibliographical references (p. 61-62).
DepartmentMassachusetts Institute of Technology. Engineering Systems Division.
Massachusetts Institute of Technology
Engineering Systems Division.