Analysis of citizens’ opinions on bills
Public engagement and open parliament
Brazil - Chamber of Deputies
Use case ID: 023
Author: Chamber of Deputies of Brazil
Date: 24 June 2024
Objective:
Read citizens’ comments on a bill, as expressed in e-polls and other participatory channels, in order to identify and categorize the main arguments for or against the bill.
Actors:
- Citizens publicly expressing their opinions
- MPs
- Communication (or engagement) unit staff
- AI system designed for semantic clustering, optionally integrated with sentence segmentation, stance detection and sentiment analysis
Prerequisites:
- Database correlating citizens’ comments with associated bills
- Automated text indexing or vectorization process, encompassing proper sentence segmentation, tokenization and semantic representation
- Database to store user feedback needed to improve the AI system
- Integration with digital services commonly used by MPs and communication staff
Scenario:
- Citizens express their opinion on a specific bill.
- Periodically, the AI system breaks down citizens’ comments into smaller sentences, subsequently creating clusters that share similar semantics and stance, whether positive or negative.
- An MP or communication staff member selects a bill (or its corresponding e-poll) to view the clusters generated by the AI system.
- The AI system offers graphical and list-based visualizations of the sentence clusters. Examples of graphical resources include word clouds and 3D spatial distributions of the sentences.
- An MP or communication staff member provides feedback on the AI-generated clusters.
Alternate flows:
- When necessary, the user can adjust the number of clusters the AI system generates.
Expected results:
- The process of analysing citizens’ comments on bills is more efficient.
- The time needed to analyse citizens’ comments on bills is reduced.
- AI system results are continuously enhanced through the accumulation of feedback over time.
Potential challenges:
- Ensuring continuous improvement of the AI system over time across various scenarios, including controversial bills and e-polls with few comments
- Addressing performance and memory issues during sentence vectorization (text embeddings) and cluster reduction
- Encouraging users to provide feedback
Data requirements:
- New comments on a given bill require the recreation of the corresponding clusters
- Periodic verification of AI system performance
Integrations with other systems:
- Digital services commonly used by MPs and communication staff
- Comment moderation tool
- Analytics and reporting tools
Success metrics:
- Amount of feedback provided by users of the AI system
- Visual inspection, a qualitative technique, allows for the visualization of clustering results using 2D or 3D graphics