Analisis Sentimen dan Persepsi Publik terhadap Pelaksanaan Program Makan Bergizi Gratis pada Media Sosial Threads
DOI:
https://doi.org/10.55606/jupikom.v5i3.7470Keywords:
sentiment analysis; emotion classification; CRISP-DM; free nutritious meal program; public policy; Threads; Indonesian NLPAbstract
Program Makan Bergizi Gratis (MBG) merupakan kebijakan strategis nasional yang menargetkan 82,9 juta penerima manfaat pada tahun 2026. Skala program yang masif memunculkan respons publik yang beragam di media sosial, khususnya Threads sebagai platform diskusi naratif. Tujuan penelitian ini bertujuan untuk menganalisis persepsi publik terhadap pelaksanaan MBG melalui pendekatan analisis sentimen berbasis aspek dan klasifikasi emosi. Metode menggunakan metodologi CRISP-DM, penelitian ini menganalisis 7.016 unggahan Threads yang telah dilabeli sentimen (positive, negative, neutral, mixed), emosi (28 kelas), dan relevansi (relevant/not relevant). Lima model machine learning dibandingkan: Logistic Regression, Linear SVC, Multinomial Naive Bayes, Complement Naive Bayes, dan Random Forest dengan representasi TF-IDF 10.000 fitur. Evaluasi menggunakan Macro F1, Weighted F1, dan 5-fold cross-validation. Analisis statistik chi-square digunakan untuk menguji asosiasi sentimen-emosi. Hasil Random Forest mencapai performa terbaik untuk deteksi relevansi (Macro F1 = 0,8751), sementara Logistic Regression unggul pada klasifikasi sentimen (Macro F1 = 0,5206) dan emosi (Macro F1 = 0,2048). Sentimen negatif mendominasi (54,3% dari 4.968 data relevan), dengan emosi frustration (37,7%) dan anger (11,4%) sebagai emosi dominan. Gabungan emosi berisiko (frustration, anger, disappointment, worry) mencapai 57,1% dari total percakapan. Uji chi-square menunjukkan asosiasi signifikan antara sentimen dan emosi (χ² = 8.313,14, p < 0,001). Fitur linguistik yang paling membedakan adalah "korupsi," "anggaran," "keracunan" pada sentimen negatif, serta "alhamdulillah," "semangat," "sehat" pada sentimen positif. Kesimpulannya analisis sentimen dan emosi pada data Threads memberikan pemahaman granular tentang persepsi publik terhadap MBG. Temuan ini dapat digunakan sebagai masukan berbasis data untuk evaluasi kebijakan dan strategi komunikasi pemerintah.
Kata Kunci: analisis sentimen, klasifikasi emosi, CRISP-DM, program MBG, kebijakan publik, Threads, NLP Indonesia
References
[1] Badan Gizi Nasional, "MBG 2026 Targetkan 82,9 Juta Penerima, Fondasi Indonesia Emas," 2026. [Online]. Availa-ble: https://www.bgn.go.id/news/berita/mbg-2026-targetkan-829-juta-penerima-fondasi-indonesia-emas
[2] Kementerian Kesehatan RI, "Pemerintah Perkuat Tata Kelola Program MBG, Keselamatan Anak Jadi Prioritas," 2026. [Online]. Availa-ble: https://kemkes.go.id/id/pemerintah-perkuat-tata-kelola-program-mbg-keselamatan-anak-jadi-prioritas
[3] Universitas Gadjah Mada, "33 Ribu Pelajar Keracunan MBG, Target 3000 Porsi per SPPG Dinilai Melebihi Kapasitas," 2026. [Online]. Availa-ble: https://ugm.ac.id/id/berita/33-ribu-pelajar-keracunan-mbg-target-3000-porsi-per-sppg-dinilai-melebihi-kapasitas/
[4] A. P. Nugroho, R. Hartono, dan S. Nurmaini, "Classification of Public Opinion on the Free Nutritional Meal Program on YouTube Media Using the LSTM Method," arXiv preprint, arXiv:2604.26312, 2026.
[5] A. R. Putri, D. Haryanto, dan F. A. Bachtiar, "Public Opinion on The MBG Program: Comparative Evaluation of InSet and VADER Lexicon Labeling Using SVM on Platform X," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 2, pp. 115–124, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9978
[6] A. Z. Muhabbab, R. Ramadhan, dan M. Fadhil, "Sentiment Analysis of Indonesia's Free Nutritious Meal Program on Platform X (Formerly Twitter) Using IndoBERT," Jurnal ZERO, vol. 6, no. 1, pp. 45–58, 2025. [Online]. Availa-ble: https://jurnal.uinsu.ac.id/index.php/zero/article/view/27629
[7] F. D. Ananda, H. Susanto, dan G. Wijaya, "Exploring Public Opinion on the 'Makan Bergizi Gratis' Program on X: A Comparative Analysis of IndoBERT-Large and NusaBERT-Large Models," Journal of Applied Informatics and Computing (JAIC), vol. 10, no. 1, pp. 33–47, 2026. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/11757
[8] R. Pratama, B. Setiawan, dan D. P. Hostiadi, "Implementation of BERTopic for Topic Modeling Analysis of the Free Nutritious Meal Program Based on YouTube Com-ments," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 3, pp. 201–215, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9754
[9] A. Kusuma, N. Lim, dan S. Karim, "Every Tweet Counts? Sentiment Analysis of Public Response Toward Indonesia's Free Nutritious Meal Program," in Proceedings of the IEEE International Conference on Data Science and Advanced Analytics (DSAA), 2025, pp. 112–121. [Online]. Available: https://ieeexplore.ieee.org/document/11248005
[10] R. Wirth dan J. Hipp, "CRISP-DM: Towards a Standard Process Model for Data Mining," in Proceedings of the 4th International Conference on the Practical Applications of Knowledge Discovery and Data Mining, Manchester, UK, 2000, pp. 29–39.
[11] Y. A. Singgalen, "Comprehensive Analysis of Sentiment and Toxicity Dynamics in Tourist Vlog Reviews: A CRISP-DM Approach," Journal of Computer System and Informatics (JoSYC), vol. 5, no. 3, pp. 512–527, 2024. doi: 10.47065/josyc.v5i3.5154
[12] F. Nugraha, A. Wibowo, dan R. Kusuma, "The Sentiment Analysis of Indonesian Startup Application Reviews Using TF-IDF+SVM and FastText: A Comparative Study," Journal of Information Technology and Computer Science (JITeCS), vol. 11, no. 1, pp. 45–59, 2026. [Online]. Available: https://jitecs.ub.ac.id/index.php/jitecs/article/view/807
[13] M. F. Kono, D. Anggraeni, dan H. Setiawan, "Comprehensive Comparison of TF-IDF and Word2Vec in Product Sentiment Classification Using Machine Learning Models," Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 5, pp. 317–328, 2026. [Online]. Avail-able: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/11582
[14] P. Zhang, Y. He, E. U. Haq, J. He, dan G. Tyson, "The Emergence of Threads: The Birth of a New Social Network," in Proceedings of the IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), 2025, pp. 88–95. [Online]. Availa-ble: https://repository.hkust.edu.hk/ir/Record/1783.1-152248
[15] R. Khairunnas, B. P. Pagua, dan T. Arifin, "User Sentiment Dynamics in Social Media: A Comparative Analysis of X and Threads," IAES International Journal of Artificial Intelligence (IJ-AI), vol. 14, no. 2, pp. 1502–1515, 2025. [Online]. Availa-ble: https://www.semanticscholar.org/paper/User-sentiment-dynamics-in-social-media%3A-a-analysis-Khairunnas-Pagua/d6054a5407a4f5f17ca1b034439ab36edcfdb0a1
[16] C. Shaw, P. LaCasse, dan L. Champagne, "Exploring Emotion Classification of Indonesian Tweets Using Large Scale Transfer Learning via IndoBERT," Social Network Analysis and Mining, vol. 15, no. 1, article 22, 2025. doi: 10.1007/s13278-025-01439-6
[17] A. Setiawan, R. Puspita, dan D. Hartanto, "Sentiment and Emotion Classification of In-donesian E-Commerce Reviews via Multi-Task BiLSTM and AutoML Benchmark-ing," arXiv preprint, arXiv:2604.24720, 2026.
[18] Badan Gizi Nasional, "Awal 2026, Program MBG Jangkau Hampir 60 Juta Penerima Manfaat," 2026. [Online]. Availa-ble: https://www.bgn.go.id/news/siaran-pers/awal-2026-program-mbg-jangkau-hampir-60-juta-penerima-manfaat
[19] J. Yushendri dan P. Musa, "Application of Natural Language Processing for Emotion Detection and Motivational Response Generation in Indonesian Text Using the CRISP-DM Method," Jurnal Sistemasi, vol. 15, no. 5, pp. 1689–1705, 2025. [Online]. Availa-ble: https://sistemasi.ftik.unisi.ac.id/index.php/stmsi/article/view/6334
[20] Kementerian Koperasi dan UKM, "Evaluasi Makan Bergizi Gratis Jateng, Menko Pangan Soroti Data dan Mutu," 2026. [Online]. Availa-ble: https://kemenkopangan.go.id/detail-berita/evaluasi-makan-bergizi-gratis-jateng-menko-pangan-soroti-data-dan-mutu
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Jurnal Publikasi Ilmu Komputer dan Multimedia
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
