A Cascaded Unsupervised-Supervised NLP Pipeline for Detecting Accusatory Language in Public Procurement

2026-08-12

AI Summary

This study addresses the underutilization of stakeholder comments and government open data in public procurement, which hinders timely detection of procedural violations. To overcome this challenge, the authors propose a lightweight, domain-adapted cascaded unsupervised–supervised NLP framework. The approach first employs domain-finetuned Word2Vec embeddings combined with Gaussian Mixture Model (GMM) clustering to uncover latent anomalous patterns; it then applies a Random Forest classifier to identify comments with accusatory intent. Despite severe class imbalance, the method achieves high precision and recall without requiring extensive computational resources, enabling effective identification of procurement risks and significantly enhancing regulatory transparency.

Abstract

Public procurement involves the allocation of substantial financial resources; therefore, continuous oversight through audits, controls, and monitoring mechanisms is essential. However, stakeholder comments and publicly available government data are often underutilized, despite their potential to reveal procedural irregularities. To address this gap, this paper analyzes metadata from Ecuador's Sistema Oficial de Contratación Pública (SOCE, Official Public Procurement System), with particular emphasis on participant comments generated during the pre-contractual phase. We propose a hybrid modeling framework that integrates unsupervised clustering and supervised classification within a natural language processing (NLP) pipeline to uncover latent patterns and detect potentially irregular procurement processes. Semantic embeddings are generated using Word2Vec, LLaMA, and RoBERTa, followed by Gaussian Mixture Models (GMMs) for unsupervised clustering. A supervised classification stage is then applied to identify accusatory or whistleblowing-style comments. Experimental results show that the combination of domain-trained Word2Vec embeddings, GMM-based clustering, and a Random Forest classifier achieves high precision and recall, even under severe class imbalance. These findings demonstrate that lightweight, domain-adapted NLP architectures can effectively support risk identification and enhance transparency in public procurement systems without requiring large-scale computational infrastructure.

Problem

• public procurement
• accusatory language
• whistleblowing
• procedural irregularities
• stakeholder comments

Innovation

• hybrid NLP pipeline
• unsupervised-supervised learning
• accusatory language detection
• domain-adapted embeddings
• public procurement transparency