Nora Fitaria, Dedi Darwis

Analisis Kinerja Decision Tree dan Naïve Bayes Pada Klasifikasi Tingkat Kepuasan Masyarakat

Introduction

Analisis kinerja decision tree dan naïve bayes pada klasifikasi tingkat kepuasan masyarakat. Klasifikasi tingkat kepuasan masyarakat dengan Decision Tree & Naïve Bayes pada data SKM layanan publik. Naïve Bayes lebih akurat (95.04%) dari Decision Tree, efisien untuk evaluasi layanan pemerintah.

Abstract

The Public Satisfaction Survey (SKM) is an official instrument used by the government to evaluate public service performance as stipulated in Regulation of the Minister of State Apparatus Empowerment and Bureaucratic Reform (PermenPANRB) Number 14 of 2017. However, the use of SKM data in many government agencies is still limited to calculating satisfaction index values without further predictive analysis. This study aims to classify the level of satisfaction of service users of the Metro City Investment and Integrated Services Agency (DPMPTSP) using the Decision Tree and Naïve Bayes algorithms. The data used is SKM data from 2025 to the fourth quarter, consisting of 2,760 respondents, which consists of nine service elements (U1–U9) with satisfaction categories as class variables. The research process includes data pre-processing, classification modeling using RapidMiner, and model evaluation based on confusion matrix, accuracy, precision, and recall. The results showed that the Naïve Bayes algorithm produced an accuracy rate of 95.04%, higher than the Decision Tree, which obtained an accuracy of 84.46%, and had a better recall value in the dominant class (recall of the Satisfied class was 98.16%). These advantages demonstrate the efficiency of the Naïve Bayes probabilistic approach in handling categorical features in public service elements. This study proves that the application of Data mining techniques to SKM data can support data-based public service evaluation.

Review

This study addresses a pertinent gap in the utilization of Public Satisfaction Survey (SKM) data within government agencies, which traditionally limits its application to merely calculating satisfaction index values rather than leveraging its predictive potential. Titled "Analisis Kinerja Decision Tree dan Naïve Bayes Pada Klasifikasi Tingkat Kepuasan Masyarakat," the research specifically aims to classify the level of satisfaction among service users of the Metro City Investment and Integrated Services Agency (DPMPTSP). By comparing the performance of Decision Tree and Naïve Bayes algorithms, the paper seeks to demonstrate how data mining techniques can enhance public service evaluation beyond basic metrics, aligning with regulatory mandates such as PermenPANRB Number 14 of 2017. The methodology employed in this research is straightforward and clearly outlined. It utilizes SKM data from the fourth quarter of 2025, comprising 2,760 respondents across nine distinct service elements (U1–U9), with satisfaction categories serving as the class variables. The analytical process involved standard data pre-processing, followed by classification modeling executed in RapidMiner, and a comprehensive evaluation based on widely accepted metrics: confusion matrix, accuracy, precision, and recall. The comparative analysis revealed that the Naïve Bayes algorithm significantly outperformed the Decision Tree, achieving an impressive accuracy rate of 95.04% compared to the latter's 84.46%. Furthermore, Naïve Bayes demonstrated superior recall for the dominant 'Satisfied' class, registering 98.16%, which the authors attribute to its efficiency in handling categorical features through a probabilistic approach. This study makes a valuable contribution by showcasing the practical utility of data mining in transforming raw SKM data into actionable insights for public service improvement. The clear demonstration of Naïve Bayes' superiority in this specific context provides a strong recommendation for its adoption by government agencies seeking to move beyond descriptive statistics into predictive analytics. The findings underscore the potential for data-driven evaluation to enhance public service performance effectively. While the research successfully validates the application of these techniques, future work could explore the interpretability aspects of the models, particularly for understanding the root causes of dissatisfaction, and potentially investigate the performance of other advanced classification algorithms or ensemble methods to further refine predictive capabilities.

Full Text

Comments

You need to be logged in to post a comment.