Similarity Sampling by Machine Learning A Social Science Experiment with Artificial Intelligence and IPCC Leadership

Abstract

In this paper, we devise a machine learning protocol to tackle a complex sociological task: extending a sample of organisational leaders starting from a list of individuals nominated for the Bureau of the Intergovernmental Panel on Climate Change. The difficulty in this task lies in the impossibility to spell out the characteristics that define leadership in a complex and highly distributed organisation. To bypass this lack of explicit definition, we use a series of techniques for anomaly detection to identify IPCC contributors with profiles similar to official Bureau nominees. We found that we can build an accurate model of IPCC leadership despite its social and political complexity and that we can usefully use that model to extend our initial sample.