Penerapan Text Mining pada Komentar Sosmed Instagram dan Youtube Mengenai Program Makan Bergizi Gratis untuk Analisis Sentimen Lintas Isu Model Indobert dan Teknik Smote
DOI:
https://doi.org/10.54065/artificial.1877Keywords:
Analisis Sentimen, IndoBERT, Makan Bergizi Gratis, Media Sosial, SMOTEAbstract
Urgensi penelitian ini adalah meningkatkan akurasi klasifikasi sentimen berbahasa Indonesia dengan mengatasi ketidakseimbangan data melalui penerapan Stopword Removal dan SMOTE. Program Makan Bergizi Gratis (MBG) merupakan kebijakan pemerintah yang memperoleh beragam respons masyarakat melalui media sosial. Instagram dan YouTube menyediakan ruang interaksi yang memungkinkan masyarakat menyampaikan dukungan, kritik, maupun tanggapan terhadap pelaksanaan program. Besarnya volume komentar menyebabkan identifikasi sentimen secara manual menjadi tidak efisien, sehingga diperlukan pendekatan text mining dan pemodelan bahasa yang mampu mengolah data teks berbahasa Indonesia dalam jumlah besar. Penelitian ini bertujuan menerapkan text mining pada komentar Instagram dan YouTube mengenai Program MBG menggunakan model IndoBERT dan teknik Synthetic Minority Over-sampling Technique (SMOTE), serta menganalisis sentimen berdasarkan isu yang berkaitan dengan program. Data dikumpulkan menggunakan teknik web scraping dan menghasilkan 52.326 komentar. Setelah proses preprocessing dan pembersihan data, sebanyak 47.861 komentar digunakan dalam analisis. Tahapan preprocessing meliputi case folding, cleaning, normalisasi kata tidak baku, tokenisasi, stopword removal, dan stemming. Data kemudian diberi label menjadi sentimen positif, netral, dan negatif. Distribusi awal terdiri atas 3.131 komentar positif, 31.136 netral, dan 4.025 negatif. Ketidakseimbangan kelas ditangani menggunakan SMOTE sebelum proses klasifikasi dengan IndoBERT. Evaluasi model dilakukan menggunakan accuracy, precision, recall, F1-score, dan confusion matrix. Hasil pengujian menunjukkan bahwa model IndoBERT dengan SMOTE menghasilkan accuracy sebesar 89,88%, precision 92,55%, recall 89,88%, dan F1-score 90,63%. Hasil confusion matrix menunjukkan bahwa kesalahan klasifikasi terutama terjadi antara kelas netral dan negatif. Analisis lintas isu menunjukkan bahwa kecenderungan sentimen berbeda pada isu-isu terkait pelaksanaan Program MBG. Hasil penelitian menunjukkan bahwa kombinasi IndoBERT dan SMOTE dapat digunakan untuk mengidentifikasi kecenderungan sentimen masyarakat pada data komentar media sosial serta memberikan gambaran yang lebih terarah mengenai respons publik terhadap pelaksanaan Program MBG.
References
Adhantoro, M. S., Haq, F. A., Hartanto, D., & Sudaryanto, A. P. (2026). IndoBERT-Based Sentiment Analysis of Electric Motorcycle Policy in Indonesia Using Instagram Data. Jurnal Penelitian Sains Teknologi, 165–181. https://doi.org/10.23917/saintek.v2i2.17021
Ahmadian, H., Abidin, T. F., Riza, H., & Muchtar, K. (2024). Hybrid Models for Emotion Classification and Sentiment Analysis in Indonesian Language. Applied Computational Intelligence and Soft Computing, 2024(1), 2826773. https://doi.org/10.1155/2024/2826773
Anaissi, A., Suleiman, B., & Zandavi, S. M. (2021). Online Tensor-Based Learning Model for Structural Damage Detection. ACM Transactions on Knowledge Discovery from Data, 15(6), 1–18. https://doi.org/10.1145/3451217
Aprilah, T., Setiadi, D. R. I. M., & Herowati, W. (2025). Enhancing Aspect-Based Sentiment Analysis via Hugging Face Fine-Tuned IndoBERT. Journal of Applied Informatics and Computing, 9(6), 3821–3830. https://doi.org/10.30871/jaic.v9i6.11409
Aribowo, A. S., Basiron, H., Yusof, N. F. A., & Khomsah, S. (2021). Cross-domain sentiment analysis model on Indonesian YouTube comment. International Journal of Advances in Intelligent Informatics, 7(1), 12. https://doi.org/10.26555/ijain.v7i1.554
Babo, D. H. P., Sidi, K. R., & Imtiyaz, H. (2026). Implementation of the free nutritious meals (MBG) program: A health policy perspective from Jakarta. Jurnal Cakrawala Promkes, 8(1), 50–59. https://doi.org/10.12928/jcp.v8i1.15522
Badriyah, Chamidy, T., & Suhartono. (2025). Application of SMOTE in Sentiment Analysis of MyXL User Reviews on Google Play Store. JISKA (Jurnal Informatika Sunan Kalijaga), 10(1), 74–86. https://doi.org/10.14421/jiska.2025.10.1.74-86
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002). SMOTE: Synthetic Minority Over-sampling Technique. Journal of Artificial Intelligence Research, 16, 321–357. https://doi.org/10.1613/jair.953
Ihalauw, S. A., Trezandy Lapatta, N., Wiria Nugraha, D., Wirdayanti, & Ar Lamasitudju, C. (2025). Analisis Sentimen Terhadap Kinerja Awal Pemerintahan Menggunakan IndoBERT Dan SMOTE Pada Media Sosial X. Jurnal Algoritma, 22(2). https://doi.org/10.33364/algoritma/v.22-2.2957
Koto, F., Rahimi, A., Lau, J. H., & Baldwin, T. (2020). IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP. Proceedings of the 28th International Conference on Computational Linguistics, 757–770. https://doi.org/10.18653/v1/2020.coling-main.66
Kristiyanti, D. A., Sanjaya, S. A., Tjokro, V. C., & Suhali, J. (2024). Dealing imbalance dataset problem in sentiment analysis of recession in Indonesia. IAES International Journal of Artificial Intelligence (IJ-AI), 13(2), 2060. https://doi.org/10.11591/ijai.v13.i2.pp2060-2072
Manoppo, M. R., Kolang, I. C., Nur Fiat, D. N., Mawara, R. M. C., Sumarno, A. D. P., Yusupa, A., & Tarigan, V. (2025). Analisis Sentimen Publik Di Media Sosial Terhadap Kenaikan PPN 12% Di Indonesia Menggunakan Indobert. Jurnal Kecerdasan Buatan dan Teknologi Informasi, 4(2), 152–163. https://doi.org/10.69916/jkbti.v4i2.322
Medantoro, G. F. S., & Muljono, M. (2026). Comparative Analysis of IndoBERT and Classic Machine Learning Models for Sentiment Classification of Education Policy on Social Media X. Journal of Applied Informatics and Computing, 10(1), 548–557. https://doi.org/10.30871/jaic.v10i1.11723
Muhabbab, A. Z., Bunyamin, B., & Hasmawati, H. (2025). Sentiment Analysis of Indonesia’s Free Nutritious Meal Program on Platform X (Formerly Twitter) Using IndoBERT. ZERO: Jurnal Sains, Matematika dan Terapan, 9(3), 884. https://doi.org/10.30829/zero.v9i3.27629
Negara, A. B. P. (2025). The influence of applying stopword removal and SMOTE on Indonesian sentiment classification. Lontar Komputer: Jurnal Ilmiah Teknologi Informasi, 14(3), 172–185. https://doi.org/10.24843/LKJITI.2023.v14.i03.p05
Perwira, R. I., Permadi, V. A., Purnamasari, D. I., & Agusdin, R. P. (2025). Domain-Specific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content. Journal of Information Systems Engineering and Business Intelligence, 11(1), 30–40. https://doi.org/10.20473/jisebi.11.1.30-40
Rifaldi, D., Abdul Fadlil, & Herman. (2023). Teknik Preprocessing Pada Text Mining Menggunakan Data Tweet “Mental Health.” Decode: Jurnal Pendidikan Teknologi Informasi, 3(2), 161–171. https://doi.org/10.51454/decode.v3i2.131
Roihan, M. R., Muhammad Itqan Mazdadi, Muliadi, Irwan Budiman, & Fatma Indriani. (2026). Comparative performance of IndoBERT-based deep learning models with SMOTE for trade tariff sentiment analysis. Journal of Soft Computing Exploration, 7(2), 432–446. https://doi.org/10.52465/joscex.v7i2.122
Salu, B. M., Irwanda, D. A., Hasibuan, N. R. K., & Arifin, S. (2026). Pengembangan Sistem Informasi Persediaan Alat Tulis Kantor Berbasis Web Di PT BPRS Amanah Bangsa. Journal Artificial: Informatika Dan Sistem Informasi, 4(1), 37–50. https://doi.org/10.54065/artificial.1104
Singgalen, Y. A. (2025). Performance Analysis of IndoBERT for Sentiment Classification in Indonesian Hotel Review Data. Journal of Information System Research (JOSH), 6(2), 976–986. https://doi.org/10.47065/josh.v6i2.6505
Suprapto, F. A., Praditya, E., Dewi, R. M., & Adiyoso, W. (2025). A Policy Implementation Review of the Free Nutritious Meal (MBG) Program. The Journal of Indonesia Sustainable Development Planning, 6(2), 297–312. https://doi.org/10.46456/jisdep.v6i2.798
Wafda, A. (2024). Integrasi Machine Learning dalam Ritel: Tinjauan Komprehensif tentang Prediksi Harga, Analisis Data Pelanggan, dan Pemanfaatan Media Sosial. Journal Artificial: Informatika Dan Sistem Informasi, 2(2), 90–106. https://doi.org/10.54065/artificial.543
Yulita, I. N., Wijaya, V., Rosadi, R., Sarathan, I., Djuyandi, Y., & Prabuwono, A. S. (2023). Analysis of Government Policy Sentiment Regarding Vacation during the COVID-19 Pandemic Using the Bidirectional Encoder Representation from Transformers (BERT). Data, 8(3), 46. https://doi.org/10.3390/data8030046
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Selvia Anggraini, Cindi Wulandari, Lukman Sunardi, Bunga Intan
This work is licensed under a Creative Commons Attribution 4.0 International License.
License and Copyright Agreement
- Authors retain copyright and other proprietary rights related to the article.
- Authors retain the right and are permitted to use the substance of the article in their own future works, including lectures and books.
- Authors grant the journal the right of first publication with the work simultaneously licensed under Creative Commons Attribution License (CC BY 4.0) 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 or self-archive 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.
