Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CitiLink: Enhancing Municipal Transparency and Citizen Engagement through Searchable Meeting Minutes

Rodrigo Silva, José Evans, José Isidro, Miguel Marques, Afonso Fonseca, Ricardo Morais, João Canavilhas, Arian Pasquali, Purificação Silvano, Alípio Jorge, Nuno Guimarães, Sérgio Nunes, Ricardo Campos

TL;DR

CitiLink tackles the transparency gap in local governance by transforming unstructured municipal meeting minutes into structured, searchable data using an NLP-driven pipeline that extracts metadata, discussed subjects, and voting outcomes with Gemini 2.0 Flash. The system stores results in MongoDB Atlas and exposes full-text and faceted search via a React frontend and Flask API, enabling efficient exploration across six Portuguese municipalities (120 minutes) with multilingual demonstrations through DeepL translations. Usability testing with municipal personnel and quantitative extraction metrics (metadata macro-F1 0.84; subjects Rouge-L 0.31; BLEU 0.21; voting macro-F1 0.67) indicate strong potential and highlight avenues for improvement. The work demonstrates a practical, scalable approach to local government transparency, and provides publicly available prompts, code, and data to facilitate adoption and extension by other municipalities and researchers.

Abstract

City council minutes are typically lengthy and formal documents with a bureaucratic writing style. Although publicly available, their structure often makes it difficult for citizens or journalists to efficiently find information. In this demo, we present CitiLink, a platform designed to transform unstructured municipal meeting minutes into structured and searchable data, demonstrating how NLP and IR can enhance the accessibility and transparency of local government. The system employs LLMs to extract metadata, discussed subjects, and voting outcomes, which are then indexed in a database to support full-text search with BM25 ranking and faceted filtering through a user-friendly interface. The developed system was built over a collection of 120 minutes made available by six Portuguese municipalities. To assess its usability, CitiLink was tested through guided sessions with municipal personnel, providing insights into how real users interact with the system. In addition, we evaluated Gemini's performance in extracting relevant information from the minutes, highlighting its effectiveness in data extraction.

CitiLink: Enhancing Municipal Transparency and Citizen Engagement through Searchable Meeting Minutes

TL;DR

CitiLink tackles the transparency gap in local governance by transforming unstructured municipal meeting minutes into structured, searchable data using an NLP-driven pipeline that extracts metadata, discussed subjects, and voting outcomes with Gemini 2.0 Flash. The system stores results in MongoDB Atlas and exposes full-text and faceted search via a React frontend and Flask API, enabling efficient exploration across six Portuguese municipalities (120 minutes) with multilingual demonstrations through DeepL translations. Usability testing with municipal personnel and quantitative extraction metrics (metadata macro-F1 0.84; subjects Rouge-L 0.31; BLEU 0.21; voting macro-F1 0.67) indicate strong potential and highlight avenues for improvement. The work demonstrates a practical, scalable approach to local government transparency, and provides publicly available prompts, code, and data to facilitate adoption and extension by other municipalities and researchers.

Abstract

City council minutes are typically lengthy and formal documents with a bureaucratic writing style. Although publicly available, their structure often makes it difficult for citizens or journalists to efficiently find information. In this demo, we present CitiLink, a platform designed to transform unstructured municipal meeting minutes into structured and searchable data, demonstrating how NLP and IR can enhance the accessibility and transparency of local government. The system employs LLMs to extract metadata, discussed subjects, and voting outcomes, which are then indexed in a database to support full-text search with BM25 ranking and faceted filtering through a user-friendly interface. The developed system was built over a collection of 120 minutes made available by six Portuguese municipalities. To assess its usability, CitiLink was tested through guided sessions with municipal personnel, providing insights into how real users interact with the system. In addition, we evaluated Gemini's performance in extracting relevant information from the minutes, highlighting its effectiveness in data extraction.
Paper Structure (4 sections, 2 figures)

This paper contains 4 sections, 2 figures.

Table of Contents

  1. Introduction
  2. System Overview
  3. Demonstration
  4. Evaluation and Future Work

Figures (2)

  • Figure 1: Architecture of the CitiLink system.
  • Figure 2: Main components of the CitiLink web interface: (a) Municipality Overview; (b) List-based view; (c) Timeline view; (d) Minute page; (e) Search interface; (f) Search results interface.