Legibot: Annotating Legislative Debate as Both Deliberative and Adversarial Practice - Evidence from the French National Assembly

We introduce Legibot, a large-scale, LLM-assisted framework for analyzing legislative debate practices in the French National Assembly during the current legislature (starting on 8 July 2024). We enrich existing frameworks like the Discourse Quality Index and adjacent deliberative-democratic scholarship and develop a rich annotation scheme that captures a range of dimensions, including tone, adherence to procedural and deliberative norms, epistemic claims, argumentative structure, emotion, and performative acts. We further train and release a lightweight supervised language model (SLM) specialized for these annotation tasks, and we deploy the fine-tuned model on the complete dataset comprising 407 126 individual sentences drawn from 149 934 speech segments. Both the annotated corpus and the SLM are made available to the research community to support reproducibility and follow-up work. Applied analyses using this multidimensional representation reveal systematic variation in justificatory practices, engagement with opponents, and affect across party lines and agenda types.The study demonstrates how theory-guided annotations, supported by LLMs, allow for bridging normative concepts coming from various visions of democracy (from deliberative to adversarial), with scalable text analysis in a core European legislature. As such, it also contributes to the current literature on the added value and limitations of generative AI in the social sciences.