Analisis Sentimen Program Makan Bergizi Gratis Menggunakan Claude Sonnet 4.5 dengan pendekatan Zero-Shot Classification
-
Yassir Ahmad Nugroho
*
Universitas Mercu Buana Yogyakarta, Yogyakarta,
Indonesia
- Mutaqin Akbar Universitas Mercu Buana Yogyakarta, Yogyakarta, Indonesia (*) Corresponding Author
Abstract
The Free Nutritious Meal Program (Program Makan Bergizi Gratis, MBG) is a national policy aimed at improving public nutritional quality, particularly among school-aged children. Despite its strategic objectives, the program’s implementation has generated diverse public responses, widely expressed through social media platforms. This study aims to analyze public sentiment toward the Free Nutritious Meal Program using the Claude Sonnet 4.5 model with a zero-shot classification approach. The study was conducted online using YouTube user comments on videos discussing the MBG program as the data source. Data were collected through the YouTube Data API between January 5 and January 20, 2026, yielding a total of 5,036 comments. After preprocessing, 4,737 clean comments were retained for analysis. Sentiment classification was performed without model retraining by leveraging the contextual understanding capabilities of Claude Sonnet 4.5. Model performance was evaluated using a Confusion Matrix by comparing automatic classification results with manual labels on 20% of the data as an evaluation sample. The results indicate that relevance classification achieved an accuracy of 97.89%, while sentiment classification reached an accuracy of 94.60%. Sentiment distribution was dominated by negative sentiment at 57.8%, followed by neutral sentiment at 21.5% and positive sentiment at 20.7%. This study contributes by proposing a Large Language Model–based framework for public policy sentiment analysis using Claude Sonnet 4.5 with a zero-shot classification approach, enabling accurate analysis of Indonesian-language public opinion without reliance on labeled training data.
Downloads
References
Amril, A., & Sazali, H. (2025). Formulasi Regulasi dan Kebijakan Komunikasi dalam Pelaksanaan Program Pembangunan: Studi pada Program Makan Bergizi Gratis. Jurnal Indonesia : Manajemen Informatika Dan Komunikasi, 6(3), 1670–1679. https://doi.org/10.63447/jimik.v6i3.1566
Area, U. M. (2024). Sarkasme Menggunakan Algoritma Support Vector Machine ( Svm ) Skripsi Oleh: Zulnandi Zidan Lubis Fakultas Teknik Sarkasme Menggunakan Algoritma Support Vector Machine ( SVM ) Skripsi Diajukan sebagai Salah Satu Syarat untuk Memperoleh Gelar Sarjana di Fakultas Teknik Universitas Medan Area.
Braga, M., Milanese, G. C., & Pasi, G. (2025). Investigating Large Language Models’ Linguistic Abilities for Text Preprocessing (Version 1). arXiv. https://doi.org/10.48550/ARXIV.2510.11482
Haromain, I., Munir, S., & Rahmah, A. (2025). Analisa Prompt Engineering pada Large Language Model dengan Retrieval-Augmented Generation untuk Informasi Obat dan Vitamin. Indonesian Journal Computer Science, 4(2), 144–153. https://doi.org/10.31294/ijcs.v4i2.10005
Iqbal, M., Sibuea, M. F. L., & Harahap, I. R. (2025). Sentiment Analysis Of Public Comments On The Free Nutritious Meal Program Using A Rule-Based Approach. Journal Of Science And Social Research, 8(3), 3705–3710. https://doi.org/10.54314/jssr.v8i3.3994
Koto, F., Beck, T., Talat, Z., Gurevych, I., & Baldwin, T. (2024). Zero-shot Sentiment Analysis in Low-Resource Languages Using a Multilingual Sentiment Lexicon. Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), 298–320. https://doi.org/10.18653/v1/2024.eacl-long.18
Muh. Subhan. (2025). Exploring Public Sentiment Toward Artificial Intelligence Apps: A Case Study of ChatGPT, Gemini, and DeepSeek in Google Apps. Journal of Information Systems Engineering and Management, 10(19s), 203–211. https://doi.org/10.52783/jisem.v10i19s.3007
Muhammad, R. N., S, L. W., & Tanggahma, B. (2024). Pengaruh Media Sosial Pada Persepsi Publik Terhadap Sistem Peradilan: Analisis Sentimen di Twitter. UNES Law Review, 7(1), 507–516. https://doi.org/10.31933/unesrev.v7i1.2327
Nurhasananda, A., & Akbar, M. (2025). Analisis Sentimen Masyarakat Terhadap Kebijakan Undang-Undang Tentara Nasional Indonesia (UU TNI) Menggunakan Support Vector Machine. Jurnal Komputer, Informasi Dan Teknologi, 5(1), 14. https://doi.org/10.53697/jkomitek.v5i1.2603
Prado-Sánchez, V.-P., Domínguez-Díaz, A., De-Marcos, L., & Martínez-Herráiz, J.-J. (2025). Zero-Shot Classification of Illicit Dark Web Content with Commercial LLMs: A Comparative Study on Accuracy, Human Consistency, and Inter-Model Agreement. Electronics, 14(20), 4101. https://doi.org/10.3390/electronics14204101
Pratiwi, A. A., & Kamayani, M. (2024). Perbandingan Pelabelan Data dalam Analisis Sentimen Kurikulum Proyek di platform TikTok: Pendekatan Naïve Bayes. Jurnal Eksplora Informatika, 14(1), 96–107. https://doi.org/10.30864/eksplora.v14i1.1093
Rahmah, H. A., Anggraini, A., Nilasari, Y. P., & Salsabilla, E. P. (2025). Analisis Efektivitas Program Makan Bergizi Gratis Di Sekolah Dasar Indonesia Tahun 2025. Integrative Perspectives of Social and Science Journal, 2(2 Mei), 2855–2866.
Ratican, J., & Hutson, J. (2024). Advancing Sentiment Analysis Through Emotionally-Agnostic Text Mining in Large Language Models (LLMS). Journal of Biosensors and Bioelectronics Research, 1–8. https://doi.org/10.47363/JBBER/2024(2)118
Rofiqi, L., & Akbar, M. (2024). Analisis Sentimen Terkait RUU Perampasan Aset dengan Support Vector Machine. JEKIN - Jurnal Teknik Informatika, 4(3), 529–538. https://doi.org/10.58794/jekin.v4i3.824
Rozak, A., Izzah, A. N. L., & Chusna, C. A. (2025). Dampak Program Makan Bergizi Gratis terhadap Konsentrasi Siswa Kelas III Sekolah Dasar. Jurnal Basicedu, 9(5), 11603–11612. https://doi.org/10.31004/basicedu.v9i5.10744
Septiana, L., Yasin, V., & Sianipar, A. Z. (2025). Analyzing public sentiment on youtube comments regarding the free lunch policy using the Support Vector Machine (SVM) algorithm. Jurnal Mandiri IT, 14(1), 129–138. https://doi.org/10.35335/mandiri.v14i1.434
Sipayung, E. M. (2024). Sentiment on Public Trust Using the NLP Rule Based Method. Jurnal Sistem Dan Teknologi Informasi (JustIN), 12(1), 175. https://doi.org/10.26418/justin.v12i1.72426
Siswoyo, B., & Utomo, N. A. P. (2025). Pemanfaatan Machine learning untuk Klasifikasi Sentimen Pelanggan pada Media Sosial. Jurnal Teknologi Informasi Digital, 1(1). https://doi.org/https://jurnal.ipdig.id/index.php/jtid/article/view/22
Suryaningtyas, N. A., Anggita, S. R., Maulida, D. R., & Misidawati, D. N. (2025). Analisis Sentimen Komentar Tiktok Dan Forecasting Keberlanjutan Program Makan Bergizi Gratis Pemerintah Dalam Perspektif Public Relations Menggunakan Model Hybrid. Jurnal Media Akademik (JMA), 3(12). https://doi.org/10.62281/xe74zg24
Taşyürek, M., Adıgüzel, Ö., & Ortaç, H. (2025). Comparative Evaluation of Responses from ChatGPT-5, Gemini 2.5 Flash, Grok 4, and Claude Sonnet-4 Chatbots to Questions About Endodontic Iatrogenic Events. Healthcare, 13(20), 2615. https://doi.org/10.3390/healthcare13202615
Wahyuni, W., Lestari, T. P., Apriliana, M., & Gumelta, R. (2025). Implementation of BERTopic for Topic Modeling Analysis of the Free Nutritious Meal Program Based on YouTube Comments. Journal of Applied Informatics and Computing, 9(4), 1964–1971. https://doi.org/10.30871/jaic.v9i4.9754
Wicaksono, B., & Nastiti, V. R. S. (2024). Analisis Sentimen dalam Opini Publik di Chanel Youtube Indonesia Lawyers Club Tentang Isu Populer dengan Menggunakan Metode LSTM dan Bi-LSTM. Jurnal Algoritma, 21(2), 241–251. https://doi.org/10.33364/algoritma/v.21-2.1696
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Analisis Sentimen Program Makan Bergizi Gratis Menggunakan Claude Sonnet 4.5 dengan pendekatan Zero-Shot Classification
Pages: 1681-1691
Copyright (c) 2026 Yassir Ahmad Nugroho, Mutaqin Akbar
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
