Search papers, labs, and topics across Lattice.
This paper introduces a computational framework combining diachronic stylometry, contextual topic modeling, and semantic clustering to analyze parliamentary discourse. Applied to a corpus of 450,000 speeches from the Brazilian Chamber of Deputies (2003-2025), the framework reveals a shift towards shorter speeches, agenda changes driven by national crises, and discursive alignments based on regional and gender identities. The study demonstrates that analyzing speech provides insights beyond traditional voting record analysis.
Forget party lines: in Brazilian politics, regional and gender identities often dictate discursive alignment more strongly.
Analyses of legislative behavior often rely on voting records, overlooking the rich semantic and rhetorical content of political speech. In this paper, we ask three complementary questions about parliamentary discourse: how things are said, what is being said, and who is speaking in discursively similar ways. To answer these questions, we introduce a scalable and generalizable computational framework that combines diachronic stylometric analysis, contextual topic modeling, and semantic clustering of deputies'speeches. We apply this framework to a large-scale case study of the Brazilian Chamber of Deputies, using a corpus of over 450,000 speeches from 2003 to 2025. Our results show a long-term stylistic shift toward shorter and more direct speeches, a legislative agenda that reorients sharply in response to national crises, and a granular map of discursive alignments in which regional and gender identities often prove more salient than formal party affiliation. More broadly, this work offers a robust methodology for analyzing parliamentary discourse as a multidimensional phenomenon that complements traditional vote-based approaches.
