<![CDATA[The effectiveness of internal government supervision remains a crucial issue, as manual reporting systems often delay case detection and lack risk prioritization. Previous studies have mainly focused on reporting mechanisms without integrating Artificial Intelligence (AI) for adaptive data analysis. This research formulates how AI integration in digital whistleblowing systems can enhance the effectiveness and responsiveness of internal supervision. This is a system development study with a locus in local government. Data were obtained through simulation of 1,000 anonymized supervision reports, analyzed using Natural Language Processing and machine learning techniques. The results show an 86% accuracy in high-risk report classification and a 71% reduction in detection time. These findings reveal novelty in using AI for automated report triage. The study recommends a gradual implementation of such systems in regional inspectorates to strengthen transparency and accountability in local government.]]>
Copyrights © 2025
