Influencing social change on a broad scale is a chronically difficult problem. But what if you could identify – and then target and train at exactly the right time – those members of a population most likely to have the greatest influence on their peers?
SFI Professor Mirta Galesic, a social scientist, and Harvard’s Barbara Grosz, a computer scientist and member of SFI’s Science Board and Science Steering Committee, took some early steps recently during a working group at SFI: Social Network Interventions: Combining Network Science and AI Decision-Making with Social Influence Theories.
The duo joined forces with researchers from the University of New Mexico’s Prevention Research Center, the University of Southern California (USC), and Microsoft Research to design, implement, and evaluate a social network intervention to encourage parents in disadvantaged areas of New Mexico to promote healthy nutrition and physical activity in their children.
The collaborators will build on experiences from USC researchers Milind Tambe and Eric Rice, who have undertaken a pilot study among homeless youth in Venice Beach, California. Tambe and Rice found that a network algorithm for identifying the most influential members of the youth’s social circles and recommending sequenced interventions was useful in designing interventions to spread information about sexually transmitted diseases and increase the rate of STD testing.
“The algorithm used in the Venice Beach project was very effective,” says Galesic. “We will discuss whether we can augment the algorithm and the overall intervention by incorporating findings about social influence from social psychology.”
Based on these discussions, Galesic, Grosz, and their colleagues plan to collect preliminary data to gauge whether their approach will work in New Mexico, then seek a broader implementation of the method.
More about the August 3-5 working group "Social Network Interventions: Combining network science and AI decision making with social influence theories."