Perbandingan Model IndoBERT dan Bi-LSTM untuk Analisis Sentimen Publik di Platform X terhadap Isu Bergabungnya Indonesia dalam Board of Peace
Rahmah Muthmainah(1*);
(1) Jurusan Ilmu Komputer, Universitas Riau, Pekanbaru, Indonesia
(*) Corresponding Author
AbstractPerkembangan diplomasi digital dan meningkatnya diskursus publik di media sosial menjadikan analisis sentimen sebagai metode yang penting untuk memetakan opini masyarakat terhadap kebijakan luar negeri Indonesia. Salah satu isu yang menarik perhatian publik adalah keputusan Indonesia bergabung dalam Board of Peace. Namun, penelitian yang membandingkan kinerja IndoBERT dan Bi-LSTM pada isu geopolitik di media sosial Indonesia masih terbatas. Penelitian ini membandingkan kedua model dalam menganalisis sentimen publik di Platform X terkait isu tersebut menggunakan kerangka CRISP-DM yang meliputi pemahaman bisnis, pemahaman data, persiapan data, pemodelan, dan evaluasi. Dataset terdiri atas 1.627 unggahan yang diperoleh melalui penyaringan 2.314 tweet melalui teknik scraping berbasis kata kunci dan dilabeli secara manual ke dalam tiga kelas sentimen, yaitu 98 Negatif, 1.383 Netral, dan 146 Positif. Ketidakseimbangan kelas ditangani dengan SMOTE, sedangkan evaluasi dilakukan pada 245 sampel uji menggunakan akurasi, presisi, recall, dan F1-score. Hasil menunjukkan IndoBERT mencapai akurasi 95,51% dan weighted F1-score 0,9514, lebih tinggi dibandingkan Bi-LSTM dengan akurasi 94,29% dan F1-score 0,9409. IndoBERT unggul pada klasifikasi kelas minoritas, sedangkan Bi-LSTM lebih efisien secara komputasi. Temuan ini menunjukkan bahwa model berbasis transformer lebih efektif dalam menangkap konteks semantik wacana geopolitik digital untuk analisis sentimen kebijakan luar negeri Indonesia.
KeywordsAnalisis Sentimen; Bi-LSTM; IndoBERT; CRISP-DM; Platform X
|
Full Text:PDF |
Article MetricsAbstract view: 12 timesPDF view: 6 times |
Digital Object Identifier https://doi.org/10.33096/busiti.v7i3.3367
|
Cite |
References
M. Rodríguez-Ibáñez, A. Casánez-Ventura, F. Castejón-Mateos, and P.-M. Cuenca-Jiménez, “A Review on Sentiment Analysis from Social Media Platforms,” Expert Systems with Applications, vol. 223, art. no. 119862, 2023, doi: 10.1016/j.eswa.2023.119862.
G. Prakoso Rizky dan W. Alrasyid, “AI-Based Sentiment Analysis of Social Media to Detect Public Opinion on Government Policies,” J. Basic Sci. Technol., vol. 14, no. 2, hal. 61–69, 2025, [Daring]. Tersedia pada: https://ejournal.iocscience.org/index.php/JBST/article/view/6481
S. M. R. U. Karim, R. A. Rasul, dan T. Sultana, “Sentiment Analysis of Social Media Data for Predicting Consumer Behavior Trends Using Machine Learning,” arXiv preprint arXiv:2510.19656, Nov. 2025, doi: 10.48550/arXiv.2510.19656.
S. Barman, “DIGITAL DIPLOMACY : THE INFLUENCE OF DIGITAL PLATFORMS ON GLOBAL DIPLOMACY,” VIDYA - A Journal of Gujarat University, vol. 3, no. 1, pp. 61–75, Jun. 2024, doi: 10.47413/vidya.v3i1.304.
M. K. Perdani, R. Afandi, S. Lusa, D. I. Sensuse, P. A. W. Putro, and S. Indriasari, “Social Media as an Instrument of Public Diplomacy in the Digital Era: A Systematic Literature Review,” Policy & Governance Review, vol. 8, no. 3, pp. 284–302, Oct. 2024, doi: 10.30589/pgr.v8i3.976.
H. N. K. Paninggiran, U. Rusadi, D. A. Wicaksana, and W. M. Aulia, “Media Spatialization in Indonesia’s Digital Political Economy: A Case Study of Platform X through Vincent Mosco’s Framework,” Brilliant International Journal of Management and Tourism, vol. 5, no. 2, pp. 170–180, Jun. 2025, doi: 10.55606/bijmt.v5i2.4507.
M. Y. Samad, N. Zattullah, F. P. Abdullah, Z. Adzel, D. A. Permatasari, P. D. Persadha, and T. Brata, “Optimizing Indonesia’s Digital Diplomacy through a Multitrack Peace Building Approach: A Case Study of the Palestine-Israel Conflict,” Jurnal Pertahanan: Media Informasi tentang Kajian dan Strategi Pertahanan yang Mengedepankan Identity, Nationalism & Integrity, vol. 9, no. 3, pp. 495–511, 2023, doi: 10.33172/jp.v9i3.19272.
F. Ardianto and Y. R. Isjchwansyah, “Indonesia’s Digital Diplomacy Analysis Towards African Region Countries,” Journal of Diplomacy & Foreign Policy, vol. 2, no. 1, 2025, doi: 10.51353/zb30ph25.
Humas, “Presiden Prabowo tandatangani piagam Board of Peace, tegaskan peran aktif Indonesia jaga implementasi solusi dua negara,” Sekretariat Kabinet Republik Indonesia, 2026. [Daring]. Tersedia pada: https://setkab.go.id/presiden-prabowo-tandatangani-piagam-board-of-peace-tegaskan-peran-aktif-indonesia-jaga-implementasi-solusi-dua-negara/
M. T. Noori, M. A. Rahman, A. Purnomo, and Aripin, “Sentiment Analysis of the Israel-Palestine Conflict on X: Insights from the Indonesian Perspective using a Long Short-Term Memory Algorithm,” Journal of Informatics and Web Engineering, vol. 4, no. 2, pp. 417–429, 2025, doi: 10.33093/jiwe.2025.4.2.27.
U. K. Das, R. S. Ani, N. Datta, I. Fahad, J. Sikder, U. Sara, and A. Chakraborty, “Enhancing Sentiment Analysis Accuracy on Social Media Comments Using a Tuned BERT Model,” Discover Computing, vol. 28, no. 1, Art. no. 198, 2025, doi: 10.1007/s10791-025-09599-x.
S. T. Kokab, S. Asghar, dan S. Naz, “Transformer-based deep learning models for the sentiment analysis of social media data,” Array, vol. 14, no. April, hal. 100157, 2022, doi: 10.1016/j.array.2022.100157.
A. U. Rehman, “Unveiling Public Opinion: A Study of Sentiment Analysis Using LSTM and Traditional Models,” in 2025 4th International Conference on Communication, Computing and Digital Systems (C-CODE), Islamabad, Pakistan, 2025, pp. 1–6, doi: 10.1109/C-CODE67372.2025.11204093.
S. Minaee, E. Azimi, and A. Abdolrashidi, “Deep-Sentiment: Sentiment Analysis Using Ensemble of CNN and Bi-LSTM Models,” arXiv preprint arXiv:1904.04206, 2019, doi: 10.48550/arXiv.1904.04206.
R. Purba, F. M. Sinaga, S. J. Pipin, and K. Kelvin, “Fine-Grained Sentiment Analysis on Big Data from Multi-Platform in Indonesia,” JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer), vol. 11, no. 1, pp. 64–75, Aug. 2025, doi: 10.33480/jitk.v11i1.6549.
N. Azahra and E. Setiawan, “Sentence-Level Granularity Oriented Sentiment Analysis of Social Media Using Long Short-Term Memory (LSTM) and IndoBERTweet Method,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 1, pp. 85–95, Feb. 2023, doi: 10.26555/jiteki.v9i1.25765.
N. S. Nasution, I. Permana, F. N. Salisah, M. Afdal, dan M. Megawati, “Analisis Sentimen Masyarakat Terhadap Kebijakan IKN Pada Periode Jokowi dan Prabowo Menggunakan Algoritma NBC, SVM, dan K-NN,” Build. Informatics, Technol. Sci., vol. 7, no. 1, hal. 157–168, 2025, doi: 10.47065/bits.v7i1.7276.
J. Deng and Y. Liu, “Research on Sentiment Analysis of Online Public Opinion Based on RoBERTa–BiLSTM–Attention Model,” Applied Sciences, vol. 15, no. 4, p. 2148, Feb. 2025, doi: 10.3390/app15042148.
M. R. K. Muhaemin, Fitriyani, dan L. S. Darfiansa, “Analysis of Public Sentiment Regarding the 2024 Jakarta Election on Platform X Using Deep Learning,” Int. J. Inf. Commun. Technol., vol. 11, no. 1, hal. 13–25, 2025, doi: 10.21108/ijoict.v11i1.9176.
S. A. Mohd Selamat, S. Prakoonwit, R. Sahandi, W. Khan, and M. Ramachandran, “Big Data Analytics—A Review of Data-Mining Models for Small and Medium Enterprises in the Transportation Sector,” Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, vol. 8, no. 3, p. e1238, 2018, doi: 10.1002/widm.1238.
J. Schneider, M. Basalla, and S. Seidel, “Principles of Green Data Mining,” in Proceedings of the 52nd Hawaii International Conference on System Sciences (HICSS), 2019, pp. 2065–2074, doi: 10.24251/HICSS.2019.250.
W. H. K. Atmaja, Haryono, A. Ramadhan, and M. Zarlis, “Examining Data Needs and Predictive Models for Broadband Take-Up Ratio Estimation through CRISP-DM and Literature Review,” Journal of Logistics, Informatics and Service Science, vol. 11, no. 6, pp. 77–91, 2024, doi: 10.33168/JLISS.2024.0605.
P. Xu, X. Ji, M. Li, and W. Lu, “Small data machine learning in materials science,” npj Computational Materials, vol. 9, no. 1, pp. 1–17, 2023, doi: 10.1038/s41524-023-01000-z.
J. Abasova, P. Tanuska, and S. Rydzi, “Big Data—Knowledge Discovery in Production Industry Data Storages—Implementation of Best Practices,” Applied Sciences, vol. 11, no. 16, p. 7648, Aug. 2021, doi: 10.3390/app11167648.
B. Wilie, K. Vincentio, G. I. Winata, S. Cahyawijaya, X. Li, Z. Y. Lim, S. Soleman, R. Mahendra, P. Fung, S. Bahar, and A. Purwarianti, “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” arXiv preprint arXiv:2009.05387, 2020, doi: 10.48550/arXiv.2009.05387.
M. D. Maulana and C. S. K. Aditya, “Perbandingan IndoBERT dan Bi-LSTM Dalam Mendeteksi Pelanggaran Undang-Undang ITE,” SINTECH (Science and Information Technology) Journal, vol. 8, no. 1, pp. 52–59, Apr. 2025, doi: 10.31598/sintechjournal.v8i1.1846.
I. Martinez, E. Viles, and I. Olaizola, “Data Science Methodologies: Current Challenges and Future Approaches,” Big Data Research, vol. 24, p. 100183, May 2021, doi: 10.1016/j.bdr.2020.100183.
R. Illahi, S. Agustian, J. Jasril, and F. Yanto, “Klasifikasi Sentimen Menggunakan Bidirectional LSTM dan IndoBERT dengan Dataset Terbatas,” ZONAsi: Jurnal Sistem Informasi, vol. 7, no. 1, pp. 74–84, 2025, doi: 10.31849/zn.v7i1.25091.
T. Ramadhan and K. Kusnawi, “Performance Comparison of IndoBERT and Bi-LSTM Models for Sentiment Analysis of Shopee App Users in Indonesia,” Journal of Applied Informatics and Computing, vol. 10, no. 2, pp. 2076–2085, Apr. 2026, doi: 10.30871/jaic.v10i2.10996.
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Buletin Sistem Informasi dan Teknologi Islam (BUSITI)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.