Paper Overview
Field: NLP Authors: Flávio Soriano, Victoria F. Mello, Pedro B. Rigueira, Gisele L. Pappa, Wagner Meira, Ana Paula Couto da Silva, Jussara M. Almeida Published: 2026-04-23 arXiv: 2604.21897
Abstract (translated)
Analysis of legislative behavior typically relies on voting records, overlooking the rich semantic and rhetorical content embedded in political speeches. This paper addresses three complementary questions about parliamentary discourse: how things are said, what is being said, and who speaks in discourse-similar ways.
To answer these questions, the authors introduce a scalable and generalizable computational framework combining diachronic stylometric analysis, contextual topic modeling, and semantic clustering of legislator speeches.
The framework is applied in a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of more than 450,000 speeches from 2003 to 2025.
Key Findings
- A long-term stylistic shift toward shorter, more direct speeches.
- Sharp redirection of the legislative agenda during national crises.
- A fine-grained map of discourse alignment in which regional and gender identities are often more salient than formal party affiliation.
Significance
Beyond the empirical findings, the work provides a robust methodology for treating parliamentary discourse as a multi-dimensional phenomenon that complements traditional vote-based approaches to legislative analysis.
--- *Auto-collected on 2026-04-27. Source: arXiv:2604.21897*