Analisis Sentimen Pengguna Twitter (X) Terhadap Program Makan Bergizi Gratis (MBG) Menggunakan Naïve Bayes Classifier Dan Support Vector Machine

Andyningtyas, Friamitha Putri (2025) Analisis Sentimen Pengguna Twitter (X) Terhadap Program Makan Bergizi Gratis (MBG) Menggunakan Naïve Bayes Classifier Dan Support Vector Machine. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5003211160-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Program Makan Bergizi Gratis (MBG) merupakan salah satu program unggulan dari presiden saat ini. Program ini dikelola oleh Badan Gizi Nasional (BGN) dan memiliki tujuan untuk meningkatkan status gizi masyarakat melalui penyediaan makanan bergizi kepada kelompok sasaran serta untuk mengatasi permasalahan stunting di Indonesia. Program MBG memunculkan berbagai tanggapan di masyarakat. Diskusi terkait isu ini sangat menarik untuk dikaji, seperti bagaimana sentimen positif dan negatif masyarakat Indonesia terhadap program ini. Penelitian ini bertujuan untuk menganalisis sentimen masyarakat Indonesia mengenai program MBG di media sosial Twitter (X). Dalam penelitian ini, dilakukan perbandingan dua algoritma, yaitu algoritma Naïve Bayes Classifier dan Support Vector Machine (SVM). Penelitian ini dilakukan pada dua periode yaitu sebelum program resmi berjalan dan sesudah program telah resmi dijalankan. Pada kedua periode data, didapatkan mayoritas tweet termasuk dalam kategori sentimen positif. Persentase kategori positif sebesar 70,5% dan kategori negatif sebesar 29,5% untuk periode data sebelum program berjalan. Sedangkan pada periode data sesudah program berjalan didapatkan persentase kategori positif sebesar 62,6% dan kategori negatif sebesar 37,4%. Pada kedua periode data, dihasilkan bahwa metode Support Vector Machine dengan kernel RBF lebih baik daripada metode Naïve Bayes Classifier dan Support Vector Machine dengan kernel linear dilihat dari skor akurasi, presisi, recall, dan AUC.
========================================================================================================================
The Free Nutritious Food Program (MBG) is one of the flagship programs of the current president. This program is managed by the National Nutrition Agency (BGN) and aims to improve the nutritional status of the community through the provision of nutritious food to target groups, as well as to address stunting problems in Indonesia. The MBG Program has elicited various responses from the public. Discussions related to this issue are very interesting to study, such as how positive and negative sentiments of the Indonesian public towards this program are. This research aims to analyze the sentiment of the Indonesian public regarding the MBG program on the social media platform Twitter (X). In this study, a comparison of two algorithms was performed, namely the Naïve Bayes Classifier and Support Vector Machine (SVM) algorithms. This research was conducted in two periods: before the program officially ran and after the program has been officially implemented. In both data periods, the majority of tweets were classified into the positive sentiment category. The percentage for the positive category was 70.5% and for the negative category was 29.5% for the data period before the program ran. Meanwhile, for the data period after the program ran, the percentage for the positive category was 62.6% and for the negative category was 37.4%. In both data periods, the Support Vector Machine method with an RBF kernel was found to be better than the Naïve Bayes Classifier method and the Support Vector Machine method with a linear kernel, as seen from the accuracy, precision, recall, and AUC scores.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Analisis Sentimen, Makan Bergizi Gratis, Naïve Bayes Classifier, Support Vector Machine. Sentiment Analysis, MBG, Naïve Bayes Classifier, Support Vector Machine.
Subjects:	Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > QA Mathematics
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User:	Friamitha Putri Andyningtyas
Date Deposited:	04 Aug 2025 06:37
Last Modified:	04 Aug 2025 06:37
URI:	http://repository.its.ac.id/id/eprint/126869

Actions (login required)

View Item