The authors present Apaf, a hybrid LLM-symbolic pipeline that operationalizes critical discourse analysis as a quantitative bipolar argumentation framework over policy text. Arguments are classified into deliberative or managerial frames, and four frame-mediated relation subtypes are produced by deterministic rules over LLM-extracted features.
- The system classifies arguments into deliberative or managerial frames.
- It produces four frame-mediated relation subtypes: agency reduction, agenda shift, instrumental support, and normative support.
- A novel dataset of 100 sub-documents of disaster-risk-reduction policy from the USA, UK, Canada, and Australia is released.
The resulting argument graphs are shown to be accurate, interpretable, and stable across jurisdictions.