Semantic Clustering of Civic Proposals: A Case Study on Brazil's National Participation Platform

2025/09/25 by Ronivaldo Ferreira, Ferreira, Ronivaldo, Guilherme da Silva +5 · 1 citation
Social Sciences · #E-Government and Public Services #FOS: Computer and information sciences #Social Media and Politics #Software Engineering (cs.SE)

paper · pdf · doi:10.48550/arxiv.2509.21292

openalex publication_date 2025/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Promoting participation on digital platforms such as Brasil Participativo has emerged as a top priority for governments worldwide. However, due to the sheer volume of contributions, much of this engagement goes underutilized, as organizing it presents significant challenges: (1) manual classification is unfeasible at scale; (2) expert involvement is required; and (3) alignment with official taxonomies is necessary. In this paper, we introduce an approach that combines BERTopic with seed words and automatic validation by large language models. Initial results indicate that the generated topics are coherent and institutionally aligned, with minimal human effort. This methodology enables governments to transform large volumes of citizen input into actionable data for public policy.

Citations

• BERTopic: Neural topic modeling with a class-based TF-IDF procedure
• Language-agnostic BERT Sentence Embedding
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Cited by

• From Pre-labeling to Production: Engineering Lessons from a Machine Learning Pipeline in the Public Sector

Related

• The GDN-CC Dataset: Automatic Corpus Clarification for AI-enhanced Democratic Citizen Consultations
• CommunityFish: A Poisson-based Document Scaling With Hierarchical Clustering
• Councils in Action: Automating the Curation of Municipal Governance Data for Research
• Social Participation Ontology: community documentation, enhancements and use examples
• Interactive Discovery System for Direct Democracy