Knowledge-Based Decision Support for E-Governance: A Semantic Analytics Platform for Public Service Delivery Optimization in Brazilian Municipal Governments

Abstract

E-governance platforms have transformed the administrative landscape of Brazilian municipal governments, generating unprecedented volumes of citizen interaction data, service delivery records, and policy implementation evidence. The conversion of this accumulated administrative knowledge into actionable decision support for municipal managers remains a largely unrealized potential. Problem Statement: Brazilian municipal e-governance systems are characterized by data fragmentation across departmental silos, inadequate knowledge integration mechanisms, and decision-making processes relying predominantly on anecdotal evidence and political intuition rather than evidence-based knowledge synthesis. Proposed System: This paper proposes SGDSS-BR, a Semantic Governance Decision Support System that integrates multi-source municipal data fusion, semantic analytics, and an administrative knowledge ontology to provide evidence-based decision support for Brazilian municipal administrators. Methodology: SGDSS-BR was designed and evaluated using a synthetic dataset of 690 municipal service delivery records simulating data patterns from medium-sized Brazilian municipalities. Key Findings: The system achieved decision recommendation accuracy of 87.8%, semantic query precision of 85.4%, and produced knowledge insights rated as highly actionable by 78.6% of municipal administrator evaluators. Applications: The platform supports public resource allocation, citizen service optimization, infrastructure maintenance planning, and inter-departmental coordination.