Analisis Sentimen Opini Publik terhadap BPI Danantara di Media Sosial X Menggunakan IndoRoBERTa dan SVM
DOI:
https://doi.org/10.29407/1cp50y79Keywords:
Analisis Sentimen, IndoRoBERTa, Media Sosial, SVMAbstract
Media sosial menjadi sumber utama opini masyarakat terhadap isu publik seperti Danantara, namun data yang dihasilkan bersifat besar, tidak terstruktur, dan mengandung variasi bahasa yang kompleks. Penelitian ini bertujuan menganalisis sentimen masyarakat terhadap isu Danantara dengan membandingkan metode Support Vector Machine (SVM) dan model IndoRoBERT. Penelitian menggunakan pendekatan kuantitatif dengan tahapan pengumpulan data media sosial, prapemrosesan teks meliputi pembersihan data, tokenisasi, dan normalisasi, kemudian ekstraksi fitur menggunakan TF-IDF untuk pemodelan SVM. Selanjutnya, pemodelan berbasis IndoRoBERT dilakukan untuk memahami konteks semantik teks secara lebih mendalam. Evaluasi kinerja model dilakukan menggunakan metrik akurasi, presisi, recall, dan F1-score. Hasil menunjukkan distribusi sentimen relatif konsisten antara kedua model, dengan accuracy SVM terhadap pseudo-label IndoRoBERTa mencapai 98% precision dan recall rata-rata 0.98, macro F1-score 0.97. IndoRoBERTa terbukti lebih stabil dalam menangani teks informal dan kontekstual. Penelitian ini menunjukkan bahwa model berbasis transformer lebih efektif digunakan untuk analisis sentimen berbahasa Indonesia pada isu publik strategis berbasis media sosial.
Downloads
References
[1] S. F. Yulianti, T. Rahmawati, P. Tawainella, N. M. Rantisi, and H. Mutiara Winata, “ANALISIS SENTIMEN KOMENTAR INSTAGRAM TERHADAP KASUS TUNTUTAN 17+8 MENGGUNAKAN ALGORITMA INDOBERT: KUALITAS KEPERCAYAAN PUBLIK,” 2025. [Online]. Available: https://jurnal.panengeninsani.com/index.php/djods
[2] A. Kurniawan Santoso, “ANALISIS SENTIMEN TWITTER BAHASA INDONESIA MENGGUNAKAN PENDEKATAN MACHINE LEARNING,” JIK), vol. 6, no. 2, 2022.
[3] D. Aby Vonega, A. Fadila, and D. Ely Kurniawan, “Analisis Sentimen Twitter Terhadap Opini Publik Atas Isu Pencalonan Puan Maharani dalam PILPRES 2024,” 2022. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[4] Friska Aditia Indriyani, Ahmad Fauzi, and Sutan Faisal, “Analisis sentimen aplikasi tiktok menggunakan algoritma naïve bayes dan support vector machine,” TEKNOSAINS : Jurnal Sains, Teknologi dan Informatika, vol. 10, no. 2, pp. 176–184, Jul. 2023, doi: 10.37373/tekno.v10i2.419.
[5] F. Bei and S. Saepudin, “ANALISIS SENTIMEN APLIKASI TIKET ONLINE DI PLAY STORE MENGGUNAKAN METODE SUPPORT VECTOR MACHINE (SVM),” 2021.
[6] B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” Oct. 2020, [Online]. Available: http://arxiv.org/abs/2009.05387
[7] Agussabeth Adelina Pasaribu et al., “Analisis Pendekatan Deep Learning Sebagai Upaya Endorsment Pendidikan,” Jurnal Pengabdian Masyarakat dan Riset Pendidikan, vol. 4, no. 2, pp. 9326–9333, Nov. 2025, doi: 10.31004/jerkin.v4i2.3120.
[8] Z. Alhaq, A. Mustopa, and J. D. Santoso, “PENERAPAN METODE SUPPORT VECTOR MACHINE UNTUK ANALISIS SENTIMEN PENGGUNA TWITTER.”
[9] A. Putra, D. Haeirudin, H. Khairunnisa, and R. Latifah, “Analisis Sentimen Masyarakat Terhadap Kebijakan PPKM Pada Media Sosial Twitter Menggunakan Algoritma Svm,” 2021.
[10] U. N. Jakarta, V. B. Lestari, and C. A. Hutagalung, “J-KOMA Journal of Computer Science and Applications Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis of Indonesian-Language Marketplaces Using SVM, Logistic Regression, and Naive Bayes,” pp. 22–2025, doi: 10.21009/j.
[11] M. I. Abidin and E. W. Pamungkas, “ANALISIS SENTIMEN TERHADAP TIMNAS INDONESIA DI PIALA ASIA 2023 DENGAN MODEL TRANSFORMER BERBAHASA INDONESIA,” Rabit : Jurnal Teknologi dan Sistem Informasi Univrab, vol. 10, no. 2, pp. 482–496, Jul. 2025, doi: 10.36341/rabit.v10i2.6142.
[12] L. Yang, B. Huang, S. Guo, Y. Lin, and T. Zhao, “A Small-Sample Text Classification Model Based on Pseudo-Label Fusion Clustering Algorithm,” Applied Sciences (Switzerland), vol. 13, no. 8, Apr. 2023, doi: 10.3390/app13084716.
[13] L. Afuan and N. Hidayat, “Sentiment Analysis of the Kampus Merdeka Program on Twitter Using Support Vector Machine and a Feature Extraction Comparison: TF-IDF vs. FastText,” Journal of Applied Data Sciences, vol. 5, no. 4, pp. 1738–1753, Dec. 2024, doi: 10.47738/jads.v5i4.436.
[14] U. N. Jakarta, V. B. Lestari, and C. A. Hutagalung, “J-KOMA Journal of Computer Science and Applications Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis of Indonesian-Language Marketplaces Using SVM, Logistic Regression, and Naive Bayes,” pp. 22–2025, doi: 10.21009/j.
[15] F. Hibban Hilmi and A. Dwi Indriyanti, “Journal of Emerging Information System and Business Intelligence Sentiment Analysis of 2024 Election Fraud Using SVM and Naïve Bayes Algorithms,” Journal of Emerging Information System and Business Intelligence, vol. 5, no. 4, pp. 353–364, 2025.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Firnanda Putra Agustinus, Moch Afaldo Danny Ardiansyah
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:
- Copyright on any article is retained by the author(s).
- The author grants the journal, right of first publication with the work simultaneously licensed under a Creative Commons Attribution License 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 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.
- The article and any associated published material is distributed under the Creative Commons Attribution-ShareAlike 4.0 International License
