Discourse-Aware Policy Analysis with Argumentation: A Hybrid LLM-Symbolic Framework for Disaster Governance
For policy analysts and governance researchers, Apaf provides a structured, inspectable method to surface implicit tensions in policy discourse, addressing a gap in computational policy analysis.
This paper introduces Apaf, a hybrid LLM-symbolic framework that operationalizes critical discourse analysis as a bipolar argumentation framework for policy documents, enabling detection of frame-mediated argument relations (e.g., agency reduction, agenda shift). The approach yields accurate, interpretable, and stable argument graphs across disaster-risk-reduction policies from four countries.
Policy documents shape governance outcomes, but their reasoning is often implicit. Participatory commitments and managerial control routinely coexist in the same text, and the tensions between them are rarely stated directly. Existing computational approaches to policy discourse cannot express the frame-mediated relations that drive these tensions, where one argument narrows or instrumentalizes another rather than rejecting it. End-to-end summarization by large language models produces fluent text but offers little structure that domain experts can inspect or contest. We present Apaf, a hybrid LLM--symbolic pipeline that operationalizes critical discourse analysis as a quantitative bipolar argumentation framework over policy text. Arguments are first classified into deliberative or managerial frames. Four frame-mediated relation subtypes (agency reduction, agenda shift, instrumental support, and normative support) are then produced by deterministic rules over LLM-extracted features. We release a novel dataset of 100 sub-documents of disaster-risk-reduction policy from the USA, UK, Canada, and Australia, and show that the resulting argument graphs are accurate, interpretable, and stable across jurisdictions.