evidoria

← Back to browse

Good practice Imported

EXPRESSO's AI Sentiment Classifier — Goiás Automates Citizen Feedback Analysis for Its State Service Network

Brazil · Goiânia · See the Brazil profile

Evidence: Descriptive / self-reported Top 83% 40/100 · Ask Evidence Copilot about this practice

Goiás's state administration secretariat (SEAD) built a Multinomial Naïve Bayes classifier to auto-sort citizen feedback on its EXPRESSO service network into a live sentiment dashboard, replacing manual review — though no accuracy or volume figures have been published.

EXPRESSO's AI Sentiment Classifier — Goiás Automates Citizen Feedback Analysis for Its State Service Network

Details

Maturity
Pilot
Promoter
Secretaria de Estado da Administração (SEAD), Government of the State of Goiás
Period
2024-2025
Keywords
public administration, service delivery, citizen feedback, sentiment analysis, machine learning

Context

EXPRESSO is Goias's citizen-service delivery model, spanning seven channels (physical stores, counter service, web, app, bot, kiosks and mail). Feedback from citizens using these channels was reviewed manually by SEAD staff, a process the agency's own team described as 'time-consuming and prone to inconsistencies.'

Activities

SEAD's team built and tested a sentiment-classification pipeline: text preprocessing (noise removal, tokenization, stemming, stopword tuning) feeding several candidate algorithms, with Multinomial Naive Bayes selected for its comparatively stronger performance at flagging negative feedback. The validated model was integrated into the state's central Data Warehouse to power a real-time dashboard with word-cloud visualisations of positive and negative comments, letting SEAD managers monitor sentiment on demand rather than wait for manual reports.

Conclusions

The published account, presented at the 2025 Conference on Digital Government Research, does not disclose accuracy figures, the volume of feedback processed, or a before/after comparison against the manual process it replaced, and the exact date the tool went live in production (as opposed to being validated with managers) is not stated. The authors describe the approach as 'a scalable and replicable framework' they hope to extend to other public service centres, but that extension has not yet been documented.

Implementation
Indicative cost
Low (< €50k) — Internal state data-team development; no separate budget disclosed.
Time to results
Short (< 1 year) — Presented at the 2025 Conference on Digital Government Research; production launch date not stated.
Staffing & skills
SEAD (Goias state secretariat) data team: Rafaela M. Rosa, Jesse D. de Souza, Camila do N. Freitas

Conditions for success

  • Integration into the state's existing central Data Warehouse rather than a standalone tool
  • Real-time dashboard letting managers monitor sentiment on demand

Common failure modes

  • No accuracy figures, feedback volume, or before/after comparison disclosed
  • Production go-live date not stated

Where it fits

Governance type
state government citizen-service agency
Scale
state (Goias, Brazil)
Income level
upper-middle-income

Commonly funded by

National / regional programmes

Indicative funding routes for practices of this type — always check each programme's current calls and eligibility rules.

Do you run this practice? Claim it — verified implementers get a public contact pathway and can propose corrections.

Data sources

Where this practice's information was retrieved from, and when.

Attachments

Similar practices you may find useful