Data-driven analysis and prediction of norm acceptance

Abstract

That norms matter for politics is a widely shared observation. Existing political science research on norm diffusion, norm localization, and contestations is, however, constrained due to methodological manageability of empirical data. To face this research challenge, we propose an interdisciplinary research collaboration between political and computer science. Using the show case of energy politics, we want to conduct unsupervised and semi-supervised content analysis and fusion with the help of automated text mining methods to analyze the influence of different types of so-called norm entrepreneurs on the public acceptance and, respectively, contestations of different energy policies.