ANALISIS SENTIMEN OPINI PUBLIK TERHADAP PROGRAM MAKAN BERGIZI GRATIS (MBG) DI MEDIA SOSIAL MENGGUNAKAN MAMBA (SELECTIVE STATE SPACE MODEL)
Keywords:
Analisis Sentimen, Mamba, Selective State Space Model, Deep Learning, Makan Bergizi Gratis, NLPAbstract
Program Makan Bergizi Gratis (MBG) merupakan salah satu kebijakan pemerintah Indonesia yang menuai beragam respons dari masyarakat di media sosial. Penelitian ini bertujuan untuk menganalisis sentimen opini publik terhadap program MBG menggunakan pendekatan deep learning berbasis Mamba (Selective State Space Model). Dataset yang digunakan terdiri dari 6.270 komentar YouTube yang telah melalui proses preprocessing dan pelabelan semi-otomatis menggunakan IndoBERT dan lexicon-based. Arsitektur Mamba dipilih karena memiliki kompleksitas komputasi linear O(n) yang lebih efisien dibandingkan Transformer. Hasil eksperimen menunjukkan bahwa model Mamba mampu mencapai performa yang unggul dengan accuracy 63,16% dan F1-Score 0,6466 dalam klasifikasi sentimen tiga kelas (positif, negatif, netral), mengungguli model baseline BiLSTM-Attention (accuracy 56,46%) dan TextCNN (accuracy 59,49%). Penelitian ini memberikan kontribusi berupa penerapan arsitektur Mamba yang masih jarang digunakan dalam domain analisis sentimen berbahasa Indonesia.
Downloads
References
[1] Badan Gizi Nasional, "Program Makan Bergizi Gratis: Panduan Pelaksanaan," Jakarta: Kementerian Kesehatan RI, 2025.
[2] Indonesia Corruption Watch (ICW), "Laporan Investigasi: Tata Kelola Program Makan Bergizi Gratis," Jakarta: ICW, 2026.
[3] B. Liu, "Sentiment Analysis and Opinion Mining," Synthesis Lectures on Human Language Technologies, vol. 5, no. 1, pp. 1–167, 2012. doi: 10.2200/S00416ED1V01Y201204HLT016.
[4] S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory," Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. doi: 10.1162/neco.1997.9.8.1735.
[5] Y. Kim, "Convolutional Neural Networks for Sentence Classification," in Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 1746–1751, 2014. doi: 10.3115/v1/D14-1181.
[6] J. Devlin, M. Chang, K. Lee, and K. Toutanova, "BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding," in Proceedings of NAACL-HLT, pp. 4171–4186, 2019.
[7] A. Vaswani *et al.*, "Attention Is All You Need," in Advances in Neural Information Processing Systems (NeurIPS), vol. 30, 2017.
[8] A. Gu and T. Dao, "Mamba: Linear-Time Sequence Modeling with Selective State Spaces," arXiv preprint arXiv:2312.00752, 2023.
[9] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, "IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP," in Proceedings of COLING, pp. 757–770, 2020.
[10] P. Zhou et al., "Attention-Based Bidirectional Long Short-Term Memory Networks for Relation Classification," in Proceedings of ACL, pp. 207–212, 2016.
[11] M. D. Hugol, "Indonesia BERT Sentiment Classification," HuggingFace Model Hub, 2023. [Online]. Available: https://huggingface.co/mdhugol/indonesia-bert-sentiment-classification
[12] A. Purwarianti and I. A. P. A. Crisdayanti, "Improving Bi-LSTM Performance for Indonesian Sentiment Analysis Using Paragraph Vector," in Proceedings of ICOICT, pp. 1–5, 2019. doi: 10.1109/ICOICT46769.2019.8987469.
[13] R. Wongso, F. A. Luwinda, B. C. Trisnajaya, O. Rusli, and D. Rudy, "News Sentiment Analysis Using BERT, LSTM, and CNN," Procedia Computer Science, vol. 216, pp. 150–159, 2022. doi: 10.1016/j.procs.2022.12.122.
[14] F. N. Fajri and M. L. Khodra, "InSet Lexicon: Evaluation of a Word List for Indonesian Sentiment Analysis in Microblogs," in Proceedings of IALP, pp. 391–394, 2017. doi: 10.1109/IALP.2017.8300625.
[15] A. Gu, K. Goel, and C. Ré, "Efficiently Modeling Long Sequences with Structured State Spaces," in International Conference on Learning Representations (ICLR), 2022.
[16] A. Gu and T. Dao, "Mamba-2: Structured State Space Duality," arXiv preprint arXiv:2405.21060, 2024.
[17] D. P. Kingma and J. Ba, "Adam: A Method for Stochastic Optimization," in Proceedings of ICLR, 2015.
[18] I. Loshchilov and F. Hutter, "Decoupled Weight Decay Regularization," in Proceedings of ICLR, 2019.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Daerobby, Dedy Arisandi, Shodik Nuryadhin (Author)
This work is licensed under a Creative Commons Attribution 4.0 International License.
