GovText — Singapore's whole-of-government NLP platform for policy text analytics

GovText is a Natural Language Processing (NLP) platform built by GovTech Singapore's Data Science and Artificial Intelligence Division (DSAID) and deployed as a standard component of the Singapore Government Tech Stack. It enables public officers across all agencies to analyse large volumes of unstructured text without specialist data-science expertise, using whole-of-government (WOG) credentials for access.
Core capabilities include: topic modelling (unsupervised identification of latent themes in text corpora with interactive dashboards); both extractive and abstractive text summarisation; sentiment analysis; feedback clustering; and custom NLP model development and hosting for agencies. Two government-specific modules address common civil-service workflows: Hansard Analysis enables officers to rapidly search and analyse parliamentary debate transcripts to draft replies to Parliamentary Questions; IM8 Q&A allows natural-language querying of Singapore's ICT Instruction Manual governance standards without reading lengthy policy documents. GovText APIs integrate with agency CRM systems and other back-end tools.
Adoption data published on the Singapore Government Developer Portal and in the OECD Observatory of Public Sector Innovation (OPSI) case study (November 2024) indicate 1,680 users logged in over a six-month window and a satisfaction score of 4.85 out of 5. The Municipal Services Office (MSO) integrated GovText's text classifier and key information extractor into its citizen-feedback CRM, reducing manual triage work. OECD OPSI nominated GovText as a public-sector innovation in 2023. No published data quantifies throughput volume, processing-time savings or cost reduction relative to baseline.

Read the full analysis: https://www.govtext.gov.sg/