Evaluasi Efektivitas Model IndoBERT : Analisis Sentimen Publik pada Komentar Youtube Terhadap Program Makan Bergizi Gratis di Indonesia
Kata Kunci:
Analisis Sentimen; IndoBERT; Makan Bergizi Gratis; YouTube.Abstrak
Program Makan Bergizi Gratis (MBG) merupakan salah satu kebijakan pemerintah yang bertujuan meningkatkan kualitas gizi masyarakat, khususnya peserta didik. Implementasi program ini menimbulkan beragam tanggapan dari masyarakat yang banyak disampaikan melalui media sosial. Tujuan dari penelitian ini adalah untuk menganalisis sentimen publik terhadap MBG berdasarkan komentar pengguna YouTube menggunakan model IndoBERT. Data penelitian diperoleh melalui proses crawling pada 161 video YouTube yang relevan dengan topik MBG dan menghasilkan 8.919 komentar. Data kemudian memasuki tahap preprocessing yang dimana dilakukan pembersihan teks sebelum dilakukan pelabelan sentimen ke dalam kategori positif, negatif, dan netral. Selanjutnya, model IndoBERT di-fine-tuning untuk melakukan klasifikasi sentimen dan akan dilakukan evaluasi menggunakan metrik accuracy, precision, recall, dan F1-score. Hasil temuan menunjukkan bahwa sentimen negatif mendominasi opini publik dengan angka sebesar 72,10%, diikuti sentimen positif sebesar 15,02% dan sentimen netral sebesar 12,87%. Model IndoBERT menghasilkan performa yang sangat baik dengan nilai accuracy 91,26%, precision 91,10%, recall 91,26%, dan F1-score 91,08%. Temuan penelitian menunjukkan bahwa model IndoBERT efektif dalam melakukan analisis sentimen publik terhadap MBG berdasarkan komentar YouTube, yang ditunjukkan melalui kinerja klasifikasi yang baik sehingga layak digunakan sebagai pendekatan dalam menganalisis opini publik berbahasa Indonesia. Hasil analisis yang diperoleh diharapkan dapat menjadi bahan pertimbangan bagi kajian evaluasi program dan pengembangan strategi implementasi MBG yang lebih efektif dan berbasis pada respons masyarakat.
Unduhan
Referensi
Afuan, L., Hidayat, N., Hamdani, H., Ismanto, H., Purnama, B. C., & Ramdhani, D. I. (2025). Optimizing BERT Models with Fine-Tuning for Indonesian Twitter Sentiment Analysis. Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications, 16(2). https://doi.org/10.58346/JOWUA.2025.I2.016
Alfreihat, M., Almousa, O., Tashtoush, Y., Alsobeh, A., Mansour, K., & Migdady, H. (2023). Emo-SL Framework: Emoji Sentiment Lexicon Using Text-Based Features and Machine Learning for Sentiment Analysis. IEEE Access, 11. https://doi.org/10.1109/ACCESS.2023.1120000
Anderson, B., Irzal, M., & Hendarno, A. (2024). Sentiment Analysis of Indonesia’s Free School Lunch Policy Using LSTM and Word2Vec on YouTube Comments. J-KOMA : Journal of Computer Science and Applications, 07(02). https://doi.org/10.21009/j
Ayman, U., Akash, M. T. A., Akhter, T., Mridul, S. Z., & Sutradhar, Y. (2026). BanglaEcomReviewCorpus: A dataset for e-commerce product review sentiment analysis. Data in Brief, 66. https://doi.org/10.1016/j.dib.2026.112663
Bastian, A. A., & Perdana, A. (2025). Sentiment Analysis of Public Comments on YouTube Regarding the Inaugural Speech of the 8th President of Indonesia Using VADER and BERT Methods. International Journal Software Engineering and Computer Science (IJSECS), 5(1). https://doi.org/10.35870/ijsecs.v5i1.3472
Durga, P., & Godavarthi, D. (2017). Deep-Sentiment An Effective Deep Sentiment Analysis Using a Decision-Based Recurrent Neural Network (D-RNN). IEEE Access.
Iansyah, K., Nurlaili, A. L., & Haromainy, M. M. Al. (2025). Comparative Analysis of IndoBERT, IndoBERTweet, and XLM-RoBERTa for Detecting Online Gambling Comments on YouTube. Bit-Tech (Binary Digital - Technology), 8(2). https://doi.org/10.32877/bt.v8i2.3257
Isnan, M., & Pardamean, B. (2026). IGAR: Indonesian government applications review for sentiment analysis dataset. Data in Brief, 66. https://doi.org/10.1016/j.dib.2026.112708
Ji, S., & Yang, B. (2026). GCR-TE: Grounded generative counterfactual rewriting for text enhanced multimodal sentiment analysis. Array, 30. https://doi.org/10.1016/j.array.2026.100849
Mahfudza, N., & Ihksan, M. (2025). Sentiment Analysis of Youtube Comments on Indonesian Presidential Candidates in 2024 using Naïve Bayes Classifier. JURIKOM (Jurnal Riset Komputer), 12(2). https://doi.org/10.30865/jurikom.v12i2.8538
Maroof, A., Wasi, S., Jami, S. I., & Siddiqui, M. S. (2024). Aspect-Based Sentiment Analysis for Service Industry. IEEE Access, 12. https://doi.org/10.1109/ACCESS.2024.3440357
Maulana Basuki, R., Muharrom, N. W., Kusuma, N. A., & Hadji, K. (2026). Implementasi Program Makan Bergizi Gratis: Evaluasi Pelaksanaan dan Tantangan Operasional. Al-Zayn : Jurnal Ilmu Sosial & Hukum, 4(1). https://doi.org/10.61104/alz.v4i1.3208
Muchlashin, A. (2026). Integrasi Pemberdayaan UMKM dan Peningkatan Gizi dalam Program MBG: Perspektif Pembangunan Sosial Anif Muchlashin. Jurnal Penelitian Dan Pendidikan IPS (JPPI), 20(1), 16–23. http://ejournal.unikama.ac.id/index.php/JPPI
Nayeem, Md. D., Rafa, Z., Nova, T. T., Rahman, Y., Pathan, A. M., & Islam, Md. M. (2026). BanglaMUSE: A Multimodal Bangla Sentiment Dataset of Text–Audio Pairs for Speech and Sentiment Analysis. Data in Brief, 112458. https://doi.org/10.1016/j.dib.2026.112458
Nugroho, M. B., Khanif Zyen, A., & Widiastuti, A. (2025). Multiclass Sentiment Analysis of Electric Vehicle Incentive Policies Using IndoBERT and DeBERTa Algorithms. Journal of Applied Informatics and Computing (JAIC), 9(3). http://jurnal.polibatam.ac.id/index.php/JAIC
Pacol, C. A., & Palaoag, T. D. (2021). Enhancing Sentiment Analysis of Textual Feedback in the Student-Faculty Evaluation using Machine Learning Techniques. European Journal of Engineering Science and Technology, 4(1). https://doi.org/10.33422/ejest.v4i1.604
Pradana, A. W., & Hayaty, M. (2019). The Effect of Stemming and Removal of Stopwords on the Accuracy of Sentiment Analysis on Indonesian-language Texts. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 4. https://doi.org/10.22219/kinetik.v4i4.912
Pringgodani, B. S., & Supriyanto, A. (2025). Sentiment Analysis of YouTube Comments on Free Lunch Program Using Machine Learning. Bit-Tech (Binary Digital - Technology), 8(2). https://doi.org/10.32877/bt.v8i2.2908
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), 2855.
Santika, S. P., Saputra, M. A., Zahra, A., & Suhartono, D. (2025). Online Gambling Promotion Detection in Indonesian YouTube Comments Using Semi-Supervised IndoBERT Classification. Procedia Computer Science, 269, 1269–1278. https://doi.org/10.1016/j.procs.2025.09.068
Setiawan, B. (2024). A Review of Sentiment Analysis Applications in Indonesia Between 2023-2024. JIEET : A Review of Sentiment Analysis Applications in Indonesia Between 2023-2024, 8(2).
Shreshthi, A. J., Spanò, S., Di Nunzio, L., Cesa, R. La, Valenti, C., Re, M., & Cardarilli, G. C. (2026). Parameter-Efficient Fine-Tuning of LLMs for Low-Power Sentiment Analysis Applications. INTERNATIONAL JOURNAL ON INFORMATICS VISUALIZATION. www.joiv.org/index.php/joiv
Siam, M. F. R., & Wafa, N. (2026). BABSA: A large scale bangla aspect based sentiment analysis dataset. Data in Brief, 65. https://doi.org/10.1016/j.dib.2026.112604
Syazali, M. R., & Yulianti, E. (2025). Classification of Economic Activities in Indonesia Using IndoBERT Language Model. Journal of Computer Science and Information, 18(2). https://doi.org/10.21609/jiki.v18i2.1446
Teddy Oswari, Murniyati, Trityanti Yusnitasari, Nurasiah, & Seviyanti Wijay. (2025). Sentiment Analysis of Indonesian YouTube Reviews About Lesbian, Gay, Bisexual, and Transgender (LGBT) using IndoBERT Fine Tuning. Lontar Komputer : Jurnal Ilmiah Teknologi Informasi, 15(01). https://doi.org/10.24843/LKJITI.2024.v15.i01.p03
Ulinuha, A., Majid, E., & Nuari, R. (2025). PERFORMANCE COMPARISON OF BERT METRICS AND CLASSICAL MACHINE LEARNING MODELS (SVM, NAIVE BAYES) FOR SENTIMENT ANALYSIS. JURNAL INOVTEK POLBENG, 10(2).
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 (JAIC), 9(4). http://jurnal.polibatam.ac.id/index.php/JAIC
Youssef, L., & Elhoussaine, Z. (2026). AraABSAMD: A novel arabic dataset for aspect-based sentiment analysis in the Moroccan education domain. Array, 30. https://doi.org/10.1016/j.array.2026.100782
Zamakhsyari, F., Suhana, R., Ramadhani, I., & Santoso, D. P. (2026). Sentiment Analysis of YouTube Comments for the Jumbo Movie Trailer Using IndoBERT. Smart Techno (Smart Technology, Informatic, and Technopreneurship), 08(1), 142–150. https://doi.org/10.59356/s
Zhao, J., Deng, O., & Jin, Q. (2026). CMSA: Addressing semantic discrepancy and context dependency in multimodal sentiment analysis. Neurocomputing, 685. https://doi.org/10.1016/j.neucom.2026.133622
Zhou, J., Gandomi, A. H., Chen, F., & Holzinger, A. (2021). Evaluating the Quality of Machine Learning Explanations: A Survey on Methods and Metrics. In Electronics (Switzerland) (Vol. 10, Number 5, pp. 1–19). MDPI AG. https://doi.org/10.3390/electronics10050593
