FERDIANORIC, DRINKY (2025) KLASIFIKASI SENTIMEN DAN PEMODELAN TOPIK PADA PROGRAM MAKAN BERGIZI GRATIS DENGAN ALGORITMA NAIVE BAYES, KNN, DAN BERTOPIC. S1 thesis, Universitas Mercu Buana Jakarta.
|
Text (HAL COVER)
01 COVER.pdf Download (556kB) | Preview |
|
![]() |
Text (BAB I)
02 BAB 1.pdf Restricted to Registered users only Download (181kB) |
|
![]() |
Text (BAB II)
03 BAB 2.pdf Restricted to Registered users only Download (153kB) |
|
![]() |
Text (BAB III)
04 BAB 3.pdf Restricted to Registered users only Download (172kB) |
|
![]() |
Text (BAB IV)
05 BAB 4.pdf Restricted to Registered users only Download (471kB) |
|
![]() |
Text (BAB V)
06 BAB 5.pdf Restricted to Registered users only Download (114kB) |
|
![]() |
Text (DAFTAR PUSTAKA)
07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (109kB) |
|
![]() |
Text (LAMPIRAN)
08 LAMPIRAN.pdf Restricted to Registered users only Download (524kB) |
Abstract
This study analyzes public sentiment toward the Free Nutritious Meal Program (Makan Bergizi Gratis/MBG), a national nutrition initiative initiated by the President of the Republic of Indonesia, Prabowo Subianto, and coordinated by the National Nutrition Agency (Badan Gizi Nasional/BGN) as the main implementing body. The program is supported by the Ministry of Primary and Secondary Education (Kementerian Pendidikan Dasar dan Menengah/Kemendikdasmen), which develops implementation guidelines for educational institutions; the Ministry of Health (Kementerian Kesehatan/Kemenkes), which is responsible for health and nutritional aspects; as well as Bappenas and UNICEF, which contribute to governance recommendations and evaluation systems. Public opinion data were collected from the social media platform Twitter, then processed through text cleaning, translation, and topic analysis using the BERTopic method to identify dominant issues. Sentiment analysis was conducted using Naïve Bayes and K-Nearest Neighbor (KNN) algorithms to classify opinions into positive, negative, and neutral categories. The aim of this research is to measure public perception in an automated and systematic manner, as well as to compare the performance of the two algorithms. The findings are expected to provide valuable input for policymakers in evaluating the program and to serve as a reference for academics and practitioners in applying machine learning and topic modeling to public policy analysis. Keyword: Analisis Sentimen, Makan Bergizi Gratis, Prabowo Subianto, Naïve Bayes, K-Nearest Neighbor, BERTopic, Twitter Penelitian ini menganalisis sentimen masyarakat terhadap Program Makan Bergizi Gratis (MBG), suatu inisiatif gizi nasional yang digagas oleh Presiden Republik Indonesia, Prabowo Subianto, dan dilaksanakan oleh Badan Gizi Nasional (BGN) sebagai koordinator utama. Program ini didukung oleh Kementerian Pendidikan Dasar dan Menengah (Kemendikdasmen) yang menyusun pedoman bagi satuan pendidikan, Kementerian Kesehatan (Kemenkes) yang bertanggung jawab pada aspek kesehatan dan gizi, serta Bappenas dan UNICEF yang berperan dalam penyusunan rekomendasi tata kelola dan sistem evaluasi. Data opini publik dikumpulkan dari media sosial Twitter, kemudian melalui proses pembersihan teks, penerjemahan, dan analisis topik menggunakan BERTopic untuk mengidentifikasi isu-isu dominan. Analisis sentimen dilakukan dengan algoritma Naïve Bayes dan K-Nearest Neighbor (KNN) untuk mengklasifikasikan opini menjadi sentimen positif, negatif, dan netral. Tujuan penelitian ini adalah mengukur persepsi publik secara otomatis dan sistematis, serta membandingkan kinerja kedua algoritma. Hasil penelitian diharapkan dapat menjadi bahan pertimbangan bagi pengambil kebijakan dalam evaluasi program dan menjadi referensi bagi akademisi maupun praktisi dalam penerapan machine learning dan topic modeling pada kebijakan publik. Kata kunci: Analisis Sentimen, Makan Bergizi Gratis, Prabowo Subianto, Naïve Bayes, K-Nearest Neighbor, BERTopic, Twitter
Actions (login required)
![]() |
View Item |