Sentiment Modeling of YouTube Comments Regarding Nickel Downstreaming Policy Using Supervised Learning Algorithms
Pemodelan Sentimen Komentar YouTube Terkait Kebijakan Hilirisasi Nikel Menggunakan Algoritma Supervised Learning
DOI:
https://doi.org/10.21070/ups.10791Keywords:
Sentiment Analysis, Nickel Downstreaming, SMOTE-Tomek Links, Supervised Learning, YouTubeAbstract
The nickel downstreaming policy since 2020 has sparked a dynamic public discussion on YouTube, but sentiment analysis often impacts class integrity, leading to model bias. This study aims to analyze public sentiment and demonstrate the effectiveness of the SMOTE-Tomek Links method in addressing data integrity in 7,850 YouTube comments (81.04% negative, 18.96% positive). Three supervised learning algorithms were tested before and after the implementation of SMOTE-Tomek Links. The results show that the best model was achieved by the Support Vector Machine (SVM) with an 80:20 ratio with SMOTE-Tomek Links, producing 96.37% accuracy and 89% positive class recall. This method effectively reduces bias by reducing the recall difference from 14% to 9%. Public opinion centers on concerns about environmental impacts, while positive sentiment focuses on industrial welfare. This study proves that the integration of SMOTE-Tomek Links significantly improves the reliability of the classification model on imbalanced public policy sentiment data.
Downloads
References
W. P. Sahputra, B. A. Badia, M. I. Putra, F. C. Putra, dan A. A. Aji, “Rekayasa Proses Ekstraksi dan Pengolahan Bijih Nikel: Teknologi, Tantangan, dan Prospek Masa Depan,” KAPALAMADA J. Multidisipliner, vol. 4, no. 02, hal. 243–255, 2025, doi: 10.62668/kapalamada.v4i02.1546.
R. B. Santoso, D. F. Moenardy, R. Muttaqin, dan D. Saputera, “Pilihan Rasional Indonesia dalam Kebijakan Larangan Ekspor Bijih Nikel,” Indones. Perspect., vol. 8, no. 1, hal. 154–179, 2023.
M. Hidayat dan U. Budiyanto, “Sentimen Analisis Tentang Hilirisasi Industri Berdasarkan Opini Masyarakat Di Twitter Menggunakan Metode K-Nearest Neighbor,” Pros. Semin. Nas. …, vol. 2, no. September, hal. 826–835, 2023.
Norlaila, W. W. Winarno, dan E. T. Luthfi, “Analisis Sentimen Masyarakat Tentang Tambang Di Indonesia Pada Twitter Menggunakan Data Mining,” JIPI (Jurnal Ilm. Penelit. dan Pembelajaran Inform., vol. 9, no. 3, hal. 1091–1099, 2024, doi: 10.29100/jipi.v9i3.5402.
A. A. Ningtyas, A. Solichin, dan R. Pradana, “Analisis Sentimen Komentar Youtube Tentang Prediksi Resesi Ekonomi Tahun 2023 Menggunakan Algoritme Naïve Bayes,” Bit (Fakultas Teknol. Inf. Univ. Budi Luhur), vol. 20, no. 1, hal. 9, 2023, doi: 10.36080/bit.v20i1.2317.
W. A. Social, “Digital 2025: Indonesia,” We Are Social & Meltwater.
M. B. Al Hakiki dan Y. Darmi, “Penerapan Algoritma Machine Learning SVM dan NBC pada Sentimen Analisis Komentar Youtube Program Pengaduan Masyarakat Lapor Mas Wapres,” J. Ilmu Multidisiplin, vol. 4, no. 1, hal. 396–410, 2025, doi: 10.38035/jim.v4i1.884.
M. I. Prayugah, U. Indahyanti, dan N. Ariyanti, “Analisis sentimen publik pada pemerintah dalam serangan ransomware dengan pendekatan smote,” vol. 8, no. 2, hal. 333–343, 2024, doi: 10.35145/joisie.v8i2.4764.
A. B. Pratama dan D. Febriawan, “Analisis Sentimen Terkait Hilirisasi Industri Pada Opini Masyarakat X dengan Menggunakan Naive Bayes,” J. Inf. Syst. Res., vol. 6, no. 2, hal. 1444–1453, 2025, doi: 10.47065/josh.v6i2.6811.
F. Destiyanti, A. I. Hadiana, dan F. R. Umbara, “Penerapan Metode Support Vector Machine dan SMOTE untuk Klasifikasi Sentimen Publik Terhadap Polisi Republik Indonesia,” Jumanji, vol. 8, no. 1, hal. 1–15, 2024.
A. Miftahusalam, A. F. Nuraini, A. A. Khoirunisa, dan H. Pratiwi, “Perbandingan Algoritma Random Forest, Naïve Bayes, dan Support Vector Machine Pada Analisis Sentimen Twitter Mengenai Opini Masyarakat Terhadap Penghapusan Tenaga Honorer,” Semin. Nas. Off. Stat., vol. 2022, no. 1, hal. 563–572, 2022, doi: 10.34123/semnasoffstat.v2022i1.1410.
K. Marzuki, L. G. Rady Putra, H. Hairani, L. Z. A. Mardedi, dan J. X. Guterres, “Performance Improvement of The Random Forest Method Based on Smote-Tomek Link on Lombok Tourism Analysis Sentiment,” J. Bumigora Inf. Technol., vol. 5, no. 2, hal. 151–158, 2024, doi: 10.30812/bite.v5i2.3166.
A. Nurhopipah dan C. Magnolia, “Perbandingan Metode Resampling pada Imbalanced Dataset untuk Klasifikasi Komentar Program MBKM,” JUPIKOM (Jurnal Publ. Ilmu Komput. dan Multimedia), vol. 1, no. 2, hal. 9–22, 2022.
A. A. Nurrahman, M. Mauladi, dan A. Rahman, “Analisis Sentimen Masyarakat terhadap Kenaikan Harga Bahan Bakar Minyak Menggunakan Support Vector Machine dan SMOTE,” J. Tek. Inform., vol. 4, no. 2, hal. 396–410, 2025, doi: https://doi.org/10.56211/sudo.v4i2.908.
P. W. S. Aji, Suprianto, dan R. Dijaya, "Prediksi Penyakit Stroke Menggunakan Metode Random Forest." Kesatria: Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) 4.4 (2023): 916-924.
E. Tohidi, R. P. Herdiansyah, E. Wahyudin, dan Kaslani, “Analisa sentimen komentar video YouTube di channel TVOneNews tentang calon presiden Prabowo Subianto menggunakan Support Vector Machine,” JATI (Jurnal Mhs. Tek. Inform., vol. 8, no. 1, hal. 660–667, 2024.
Y. Findawati, U. Indahyanti, Y. Rahmawati, dan R. Puspitasari, “Sentiment Analysis of Potential Presidential Candidates 2024: A Twitter-Based Study,” Acad. Open, vol. 8, no. 1, hal. 1–17, 2023, doi: 10.21070/acopen.8.2023.7138.
H. Bichri, A. Chergui, dan M. Hain, “Investigating the Impact of Train / Test Split Ratio on the Performance of Pre-Trained Models with Custom Datasets,” IJACSA, vol. 15, no. 2, hal. 331–339, 2024.
B. W. Rauf, “Sentimen Analisis Pertambangan Di Konawe Utara Dengan Metode Naïve Bayes,” Pros. Semin. Nas. Pemanfaat. Sains dan Teknol. Inf., vol. 1, no. 1, hal. 97–102, 2023.
Downloads
Additional Files
Posted
Categories
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
