Similarity Sampling by Machine Learning A Social Science Experiment with Artificial Intelligence and IPCC Leadership
Fiche du document
7 décembre 2020
- handle: 10670/1.ln1hlc
- hal: hal-03043440
info:eu-repo/semantics/OpenAccess
Sujets proches
Learning, Machine Pattern ModelCiter ce document
Tommaso Venturini et al., « Similarity Sampling by Machine Learning A Social Science Experiment with Artificial Intelligence and IPCC Leadership », HAL-SHS : sociologie, ID : 10670/1.ln1hlc
Métriques
Partage / Export
Résumé
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.