MDAF: A Multi-Dimensional Annotation Framework for Automated Foreign Policy Analysis

Government websites contain a vast but underexploited body of textual evidence on foreign policy. This article develops a scalable approach for extracting structured information from policy texts and converting it into standardized event data, with policy event defined broadly as a statement or action. It proposes MDAF integrating an LLM workflow to automate foreign policy text identification, information extraction, and event classification. Empirically, it applies this approach to China-related texts from Five Eyes countries. The analysis shows that the resulting database supports systematic cross-national comparison, reveals variation in how states frame and implement China policy, and traces the temporal evolution of these policy profiles. This article contributes to foreign policy analysis and the methodological development of computational international relations.