Analisis Sentimen Ulasan Pengguna Aplikasi Mobile SP4N-LAPOR! Dengan Pendekatan Machine Learning Untuk Optimalisasi Pengelolaan Pengaduan Masyarakat

Sulistiowati, Yeni (2025) Analisis Sentimen Ulasan Pengguna Aplikasi Mobile SP4N-LAPOR! Dengan Pendekatan Machine Learning Untuk Optimalisasi Pengelolaan Pengaduan Masyarakat. Masters thesis, Institut Teknologi Sepuluh Nopember.

[thumbnail of 6032231247__Yeni Sulistiowati__AB.pdf] Text
6032231247__Yeni Sulistiowati__AB.pdf
Restricted to Repository staff only

Download (7MB) | Request a copy

Abstract

Perkembangan teknologi informasi di Indonesia telah meningkatkan angka akses internet, hingga kini mencapai 79,5% dari total populasi. Hal ini membuka peluang besar bagi digitalisasi pelayanan publik, termasuk implementasi Sistem Pengelolaan Pengaduan Pelayanan Publik Nasional (SP4N-LAPOR!). Aplikasi ini memfasilitasi masyarakat dalam menyampaikan pengaduan secara cepat dan transparan, termasuk melalui perangkat mobile yang semakin populer. Beberapa analisis sebelumnya hanya mengevaluasi secara kualitatif dan kuantitatif deskriptif, sehingga pengalaman dan perspektif masyarakat sebagai pengguna aplikasi belum tergambarkan secara utuh. Oleh karena itu, penelitian ini mengusulkan penggunaan teknik analisis sentimen terhadap ulasan masyarakat di aplikasi mobile berbasis Android dalam mengidentifikasi masalah teknis serta gambaran kualitas pelayanan dari penyelenggara. Penelitian ini menggunakan pendekatan Machine Learning dengan model Naïve Bayes (NB), Support Vector Machine (SVM), dan kombinasi keduanya (NBSVM) dengan tambahan fitur ekspansi N-gram. Dari ketiga model yang diuji, NBSVM menunjukkan performa terbaik dengan G-Mean sebesar 0.8451, Sensitivity sebesar 0.8227 dan F2 Score sebesar 0.8215, lebih unggul dibandingkan NB dan SVM. Model terbaik ini digunakan sebagai dasar dalam pengembangan dashboard bagi manajemen. Hasil evaluasi dengan SUS Score sebesar 72.8 menunjukkan bahwa dashboard dapat digunakan dengan cukup baik dan membantu pengguna dalam memahami tren dan dinamika opini publik secara real-time.
==================================================================================================================================
The development of information technology in Indonesia has significantly increased internet access, now reaching 79.5% of the total population. This growth presents a major opportunity for the digitalization of public services, including the implementation of the National Public Service Complaint Management System (SP4N-LAPOR!). The application enables the public to submit complaints quickly and transparently, including via increasingly popular mobile devices. However, previous analyses have mostly been limited to qualitative and descriptive quantitative approaches, which do not fully reflect the experiences and perspectives of the public as primary users. Therefore, this study proposes the use of sentiment analysis techniques on user reviews from the Android-based mobile application to identify technical issues and provide an overview of service quality. The study applies a Machine Learning approach using three models: Naïve Bayes (NB), Support Vector Machine (SVM), and a hybrid model (NBSVM), enhanced with N gram feature expansion. Among the three models tested, NBSVM achieved the best performance with a G-Mean of 0.8451, Sensitivity of 0.8227, and F2 Score of 0.8215, outperforming both NB and SVM. This best-performing model was then used as the foundation for developing a management dashboard. Evaluation results using the System Usability Scale (SUS) showed a score of 72.8, indicating that the dashboard has good usability and supports users in effectively understanding trends and the dynamics of public opinion in real-time.

Item Type: Thesis (Masters)
Uncontrolled Keywords: Analisis Sentimen, Aplikasi Mobile SP4N LAPOR!, Naive Bayes, NBSVM, N-gram, Ombudsman RI, Support Vector Machine, Sentiment Analysis, SP4N-LAPOR! Mobile Application
Subjects: H Social Sciences > H Social Sciences (General)
H Social Sciences > HA Statistics
Q Science
Q Science > Q Science (General)
Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines.
Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science)
Q Science > QA Mathematics > QA9.58 Algorithms
T Technology > T Technology (General)
T Technology > T Technology (General) > T57.8 Nonlinear programming. Support vector machine. Wavelets. Hidden Markov models.
Divisions: Interdisciplinary School of Management and Technology (SIMT) > 61101-Master of Technology Management (MMT)
Depositing User: Yeni Sulistiowati
Date Deposited: 03 Jun 2025 08:02
Last Modified: 03 Jun 2025 08:02
URI: http://repository.its.ac.id/id/eprint/119124

Actions (login required)

View Item View Item