Analisis Sentimen Multi-Platform Media Sosial pada Program Makan Bergizi Gratis Menggunakan Ensemble IndoBERT-SVM
DOI:
https://doi.org/10.30865/jurikom.v13i1.9460Keywords:
IndoBERT, Multi-Platform, Soft Voting Ensemble, Support Vector Machine, Sentiment AnalysisAbstract
Sentiment analysis of public policy on social media faces significant challenges due to linguistic heterogeneity across platforms and limitations of single models in capturing the diversity of opinion expressions. Previous studies tend to employ single-platform and single-model approaches that potentially generate representational bias and accuracy degradation of up to 12–15% when applied to different platform contexts. This study aims to develop a soft voting-based ensemble model that integrates Support Vector Machine (SVM) and IndoBERT to analyze public sentiment toward the Free Nutritious Meal (MBG) Program across multiple platforms, and to evaluate the effectiveness of the ensemble approach compared to single models in addressing variations in linguistic characteristics of digital platforms. The research dataset consists of 7,500 comments from X, TikTok, and YouTube collected from January 6 to September 28, 2025, processed through informal Indonesian language preprocessing, lexicon-based labeling, and stratified split division. Results demonstrate that SVM performs optimally on TikTok (accuracy 98.1%, macro F1 98.0%) but weakly on the neutral class in X (F1 51.0%), while IndoBERT excels in handling pragmatic ambiguity in X (neutral F1 74.0%) despite slightly declining on TikTok (macro F1 93.0%). The ensemble model produces the most balanced performance with accuracies of 92.53% (YouTube), 95.73% (TikTok), 92.53% (X), and macro F1 scores of 85.07%, 94.33%, 84.92% respectively. The contributions of this research include the development of a multi-platform sentiment analysis approach that addresses single-platform bias, improved classification generalization capability across heterogeneous digital ecosystems, and provision of evidence-based evaluation instruments for improving government policy implementation and communication.
References
[1] R. Puspa, I. Sarifah, and M. Yunus, “Dampak Makan Bergizi Gratis terhadap Minat Belajar Siswa Kelas 5 SD,” Pendas: Jurnal Ilmiah Pendidikan Dasar, vol. 10, no. 2, pp. 381–392, 2025, doi: 10.23969/jp.v10i02.25526.
[2] E. Triningsih, M. Afdal, I. Permana, and N. E. Rozanda, “Analisis Sentimen Terhadap Program Makan Bergizi Gratis Menggunakan Algoritma Machine Learning Pada Sosial Media X,” Building of Informatics, Technology and Science (BITS), vol. 6, no. 4, pp. 2240–2250, 2025, doi: 10.47065/bits.v6i4.5123.
[3] H. Jayadianti, W. Kaswidjanti, A. T. Utomo, and S. Saifullah, “Sentiment Analysis of Indonesian Reviews Using Fine-Tuning IndoBERT and R-CNN,” ILKOM Jurnal Ilmiah, vol. 14, no. 3, pp. 348–354, 2022, doi: 10.33096/ilkom.v14i3.1223.348-354.
[4] D. Nuryadi et al., “Fine Tuning IndoBERT untuk Analisis Sentimen pada Ulasan Pengguna Aplikasi Tiket.com di Google Play Store,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 2, pp. 3577–3583, 2025.
[5] S. Aras, M. Yusuf, R. Ruimassa, E. A. B. Wambrauw, and E. B. Palalangan, “Sentiment Analysis on Shopee Product Reviews Using IndoBERT,” Journal of Information Systems and Informatics, vol. 6, no. 3, pp. 1616–1627, 2024, doi: 10.51519/journalisi.v6i3.814.
[6] P. Ashari, N. Mutiah, and D. Prawira, “Perbandingan Kinerja Model Deep Learning BERT dan GPT dalam Analisis Sentimen Komentar Video Youtube (Studi Kasus: Film Dirty Vote),” JEPIN (Jurnal Edukasi dan Penelitian Informatika), vol. 11, no. 1, pp. 66–75, 2025.
[7] A. Y. Pratama, G. A. Sanjaya, N. K. Lubis, and M. R. Aditya, “Analisis Sentimen Publik Terkait Danantara Menggunakan Algoritma IndoBERT pada Platform Media Sosial,” METIK Jurnal, vol. 9, no. 1, pp. 92–99, 2025.
[8] N. P. V. D. Saraswati, N. Yudistira, and P. P. Adikara, “Analisis Sentimen terhadap Perundungan Siber pada Twitter menggunakan Algoritma Bidirectional Encoder Representations from Transformer (BERT),” Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 7, no. 2, pp. 909–916, 2023.
[9] N. Agustina and C. N. Ihsan, “Pendekatan Ensemble untuk Analisis Sentimen Covid-19 Menggunakan Pengklasifikasi Soft Voting,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 10, no. 2, pp. 263–270, Apr. 2023, doi: 10.25126/jtiik.2023106215.
[10] M. F. Cahyadi and T. H. Rochadiani, “Implementasi Ensemble Deep Learning untuk Analisis Sentimen terhadap Genre Game Mobile,” Jurnal Media Informatika Budidarma, vol. 8, no. 3, pp. 1512–1523, 2024, doi: 10.30865/mib.v8i3.7234.
[11] N. R. Setiawan and E. R. Kaburuan, “Sentimen Analisis Review Aplikasi Digital Korlantas Pada Google Play Store Menggunakan Metode SVM,” Jurnal SISFOKOM, vol. 12, no. 1, pp. 105–116, 2023, doi: 10.32736/sisfokom.v12i1.1489.
[12] M. I. K. Sinapoy, Y. Sibaroni, and S. S. Prasetyowati, “Comparison of LSTM and IndoBERT Method in Identifying Hoax on Twitter,” Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 3, pp. 657–662, 2023, doi: 10.29207/resti.v7i3.4912.
[13] N. K. A. Krisnasari, I. M. A. D. Suarjaya, and I. M. S. Raharja, “Classification of Public Figures Sentiment on Twitter Using Big Data Technology,” JITE (Journal of Informatics and Telecommunication Engineering), vol. 6, no. 1, pp. 157–169, 2022.
[14] S. Uyun, R. P. Rosalin, L. V Sari, and H. H. Sucinta, “A Hybrid Classification Model Based on BERT for Multi-Class Sentiment Analysis on Twitter,” JITEKI: Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 11, no. 2, pp. 194–205, 2025.
[15] D. Napitupulu, R. Fauzi, and M. Lubis, “Sentiment Analysis on Indonesian Tweets about the 2024 Election,” Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 9, no. 1, pp. 44–53, 2025.
[16] R. Agustina, A. U. El Majid, and R. Nuari, “Performance Comparison of BERT Metrics and Classical Machine Learning Models (SVM, Naïve Bayes) for Sentiment Analysis,” INOVTEK Polbeng – Seri Informatika, vol. 10, no. 2, pp. 1–10, 2025.
[17] A. N. Syafia, M. F. Hidayattullah, and W. Suteddy, “Studi Komparasi Algoritma SVM dan Random Forest pada Analisis Sentimen Komentar YouTube,” JPIT, 2024.
[18] B. Winarko and others, “The Halodoc’s Social Media Data Analysis Amidst Covid-19 Pandemic: An Evidence from Indonesia,” Jurnal Sosial Humaniora (JSH), 2021.
[19] S. K. Syari, S. P. Simarmata, and K. Widyanti, “From Privacy to Oblivion: The Right to Be Forgotten in Indonesia’s Social Media Platforms,” Law Journal, vol. 6, no. 1, 2025, doi: 10.46576/lj.v6i1.6895.
[20] A. M. U. Albab, “Optimization of the Stemming Technique on Text Preprocessing,” Transformatika: Jurnal Bahasa, Sastra, dan Pembelajaran, vol. 6, no. 1, 2023.
[21] J. T. I. dan Ilmu Komputer, “Perbandingan Algoritma Stemming Porter, Sastrawi, Idris, dan Arifin–Setiono untuk Bahasa Indonesia,” JTIIK, vol. 12, no. 2, 2025.
[22] A. B. Mutiara, “Improving the Accuracy of Text Classification using Stemming,” J Big Data, vol. 8, no. 4, 2021.
[23] T. Salsabilla and D. Alita, “Analisis Sentimen Inses di Social Media menggunakan Algoritma Naïve Bayes,” JPIT, vol. 9, no. 3, 2024, doi: 10.30591/jpit.v9i3.6611.
[24] R. R. Gunawan and D. Y. Rahayu, “Evaluation Analysis of the Necessity of Stemming and Stopword Removal in Indonesian Text Classification,” Jurnal Matrik, vol. 19, no. 1, 2023.
[25] N. Adila, “Implementation of Web Scraping for Journal Data Collection on the SINTA Website,” Sinkron: Jurnal dan Penelitian Teknik Informatika, vol. 7, no. 4, 2022.
[26] R. Anggoro, “Exploring Stemming Techniques in Ambon Malay Languages,” Jurnal Teknologi Informasi UNG, vol. 9, no. 2, 2024.
[27] R. L. Mustofa and B. Prasetiyo, “Sentiment analysis using lexicon-based method with Naive Bayes classifier algorithm on #newnormal hashtag in Twitter,” in Journal of Physics: Conference Series, 2021, p. 42155. doi: 10.1088/1742-6596/1918/4/042155.
[28] R. Oktafiani, A. Hermawan, and D. Avianto, “Pengaruh Komposisi Split Data terhadap Performa Klasifikasi Penyakit Kanker Payudara Menggunakan Algoritma Machine Learning,” Jurnal Sains dan Informatika (JSI), vol. 9, no. 1, pp. 45–54, 2023, doi: 10.34128/jsi.v9i1.622.
[29] N. Hafidz and D. Y. Liliana, “Klasifikasi Sentimen pada Twitter Terhadap WHO Terkait Covid-19 Menggunakan SVM, N-Gram, PSO,” Jurnal RESTI, vol. 5, no. 2, pp. 213–219, 2021, doi: 10.29207/resti.v5i2.2960.
[30] F. Illia, M. P. Eugenia, and S. A. Rutba, “Sentiment Analysis on PeduliLindungi Application Using TextBlob and VADER Library,” in International Conference on Data Science and Official Statistics (ICDSOS), 2021, pp. 278–288. doi: 10.34123/icdsos.v2021i1.236.
[31] M. Desiawan and A. Solichin, “SVM Optimization with Grid Search Cross Validation for Improving Accuracy of Schizophrenia Classification Based on EEG Signal,” Jurnal Teknik Informatika, vol. 17, no. 1, pp. 10–20, 2024, doi: 10.15408/jti.v17i1.37422.
[32] L. Geni, E. Yulianti, and D. S. Indra, “Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models,” JITEKI, vol. 9, no. 3, pp. 746–757, 2023, doi: 10.26555/jiteki.v9i3.26490.
[33] C. J. L. Tobing, I. G. W. Wijayakusuma, and L. P. I. Harini, “Perbandingan Kinerja IndoBERT dan mBERT untuk Deteksi Berita Hoaks Politik dalam Bahasa Indonesia,” Jurnal Sains dan Teknologi, vol. 14, no. 1, pp. 114–123, 2025.
[34] A. A. P. Simarmata and T. B. Sasongko, “Sentiment Analysis on BRImo Application Reviews Using IndoBERT,” Journal, 2023.
[35] A. N. Nurrahman, R. Ramadhani, and A. Rahman, “Sentiment Analysis of Indonesian Datasets Based on a Hybrid Deep-Learning Strategy,” Indonesian Journal of Electrical Engineering and Computer Science, vol. 29, no. 2, pp. 950–958, 2023.
[36] D. H. Handayani and T. K. Nur, “The Hybrid of BERT and Deep Learning Models for Indonesian Sentiment Analysis,” Bulletin of Electrical Engineering and Informatics, vol. 13, no. 1, pp. 221–230, 2024.
