Analisis Sentimen Warganet terhadap Program Makan Bergizi Gratis (MBG) Menggunakan Model IndoBERT
Downloads
Penelitian ini bertujuan untuk mengidentifikasi sentimen warganet terhadap Program Makan Bergizi Gratis (MBG) melalui analisis teks pada platform Twitter/X. Sebanyak 361 tweet dikumpulkan melalui proses scraping dan dipreproses melalui beberapa tahap, termasuk case folding, pembersihan teks, normalisasi, tokenisasi BERT, serta padding dan truncation. Model IndoBERT digunakan sebagai model utama untuk klasifikasi sentimen dan dilatih kembali (fine-tuning) menggunakan dataset berlabel tiga kategori, yaitu positif, negatif, dan netral. Hasil eksperimen menunjukkan bahwa model IndoBERT mampu melakukan klasifikasi dengan tingkat akurasi sebesar 60,27%, dengan nilai precision, recall, dan F1-score yang relatif seimbang. Distribusi sentimen memperlihatkan bahwa opini negatif sedikit lebih dominan dibandingkan sentimen positif dan netral. Sementara itu, confusion matrix mengindikasikan bahwa kelas netral merupakan kategori yang paling sulit dibedakan oleh model. Secara keseluruhan, penelitian ini menunjukkan bahwa IndoBERT dapat menjadi pendekatan yang efektif dalam menganalisis sentimen kebijakan publik di media sosial, meskipun kinerja model masih dapat ditingkatkan melalui perluasan dataset dan pelabelan manual yang lebih akurat.
Bakshi, R. K., Kaur, N., & Kaur, R. (2020). Opinion mining and sentiment analysis using neural networks. Procedia Computer Science, 173, 312–321.
Boyd, D., & Crawford, K. (2019). Critical questions for big data: Challenges for social media research. Information, Communication & Society, 15(5), 662–679.
Cahyani, R. N., & Adriani, M. (2021). Neural machine translation for Indonesian-English using Transformer architecture. Journal of Big Data, 8(1), 1–15.
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of NAACL-HLT (pp. 4171–4186).
Jurafsky, D., & Martin, J. H. (2023). Speech and language processing (3rd ed.). Pearson.
Koto, F., Lau, J. H., & Baldwin, T. (2020). IndoBERTweet: A pretrained language model for Indonesian social media text. In Proceedings of the 2020 Workshop on Asian Language Resources (pp. 17–25).
Kumar, A., & Jaiswal, A. (2023). Text preprocessing techniques in natural language processing. International Journal of Artificial Intelligence Research, 7(2), 55–64.
Liu, B. (2020). Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge University Press.
Mahendra, R., Rahmad, K., Awang, A., & Sari, N. (2021). IndoLEM: A benchmark dataset for Indonesian NLP tasks. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics.
Medhat, W., Hassan, A., & Korashy, H. (2014). Sentiment analysis algorithms and applications: A survey. Ain Shams Engineering Journal, 5(4), 1093–1111.
Minaee, S., Kalchbrenner, N., Cambria, E., Nikzad, N., Chenaghlu, M., & Gao, J. (2021). Deep learning–based text classification: A comprehensive review. ACM Computing Surveys, 54(3), 1–40.
Pak, A., & Paroubek, P. (2010). Twitter as a corpus for sentiment analysis and opinion mining. In Proceedings of the International Conference on Language Resources and Evaluation (LREC) (pp. 1320–1326).
Pratama, Y., & Nugraha, R. (2021). Sentiment analysis on public opinion of government policies using BERT and SVM. Indonesian Journal of Artificial Intelligence and Data Mining, 4(2), 102–109.
Putri, D. A., Kurniawan, S., & Pratama, Y. (2022). Sentimen pengguna terhadap layanan e-commerce menggunakan Long Short-Term Memory. Jurnal Teknologi Informasi dan Komputer, 7(1), 45–53.
Rahman, A., & Wibowo, H. (2023). Analisis sentimen kebijakan subsidi BBM menggunakan Support Vector Machine. Jurnal Informatika Indonesia, 9(2), 112–120.
Sari, M., & Gunawan, A. (2023). Analisis sentimen kebijakan pendidikan menggunakan metode lexicon-based. Jurnal Data Mining Indonesia, 5(3), 88–95.
Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019). How to fine-tune BERT for text classification? In China National Conference on Chinese Computational Linguistics (pp. 194–206).
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., ... & Polosukhin, I. (2017). Attention is all you need. In Advances in Neural Information Processing Systems (pp. 5998–6008).
Wilie, B., Vincentio, K., & Putra, P. (2020). IndoBERT: A pretrained language model for Indonesian NLP tasks. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP).
Yuliani, S., & Prasetyo, D. (2024). Analisis sentimen program Kartu Prakerja menggunakan IndoBERT. Jurnal Sistem Cerdas, 12(1), 33–41).
Yunitasari, F., & Hasanah, N. (2022). Analisis sentimen masyarakat terhadap kebijakan PPKM menggunakan BERT. Jurnal Teknologi Informasi dan Komputer, 8(1), 55–62.
Copyright (c) 2026 M. Haikal, Adhitia Erfina
This work is licensed under a Creative Commons Attribution-ShareAlike 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 a Creative Commons Attribution-ShareAlike 4.0 International (CC-BY-SA). that allows others to share the work with an acknowledgement 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 acknowledgement 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.
