Analisis Sentimen Publik Pengesahan UU TNI Di Media Sosial X Menggunakan SVM
Abstract
The ratification of the Indonesian National Armed Forces Bill (RUU TNI) into law by the House of Representatives (DPR RI) on March 20, 2025, sparked various public reactions. Several articles, such as Article 7(2)(b) and Article 47(2), are considered to potentially revive the military’s dual function and threaten democracy and civilian supremacy. Many people expressed their opinions on social media platform X (Twitter). This study analyzes public sentiment toward the TNI Law using the Support Vector Machine (SVM) method with 1,001 tweets collected via web scraping and processed through cleansing, tokenization, and stemming. SVM classified the sentiments into positive, neutral, and negative categories, achieving an accuracy of 94.66%. The highest recall was found in neutral sentiment (1.00), followed by positive (0.98), and negative (0.88). The results showed that negative and neutral sentiments were the most prevalent, providing recommendations to the government for more participatory and democratic policymaking.
Keywords: Sentiment Analysis; Support Vector Machine; TNI Law; Social Media; Web Scraping; Text Classification; Public Policy
Abstrak
Pengesahan RUU TNI menjadi Undang-Undang oleh DPR RI pada 20 Maret 2025 memicu berbagai reaksi masyarakat. Beberapa pasal, seperti Pasal 7 ayat (2) huruf b dan Pasal 47 ayat (2), dinilai bisa menghidupkan kembali dwifungsi militer dan mengancam demokrasi serta supremasi sipil. Masyarakat pun ramai menyampaikan pendapatnya di media sosial X (Twitter). Penelitian ini menganalisis sentimen publik terhadap UU TNI dengan metode Support Vector Machine (SVM) menggunakan 1001 cuitan yang dikumpulkan lewat web scraping dan diproses melalui cleansing, tokenisasi, dan stemming. SVM mengklasifikasikan sentimen menjadi positif, netral, dan negatif, dengan akurasi 94,66%. Recall tertinggi ada di sentimen netral (1,00), lalu positif (0,98), dan negatif (0,88). Hasilnya, sentimen negatif dan netral paling banyak muncul, memberikan masukan bagi pemerintah untuk merumuskan kebijakan yang lebih partisipatif dan demokratis.
Keywords
References
M. Z. Habibie, Y. S. P. Sihaloho, R. M. Andeka, M. A. Kiansantang, C. Irawan, dan K. Amaliah, "Yayasan Lembaga Bantuan Hukum Indonesia (YLBHI) Menolak Upaya Menghidupkan Kembali Dwi Fungsi Melalui Revisi UU TNI (Tentara Negara Indonesia)," Quantum Juris: Jurnal Hukum Modern, vol. 7, no. 2, pp. 157-168, 2025.
U. Hamid, "Menimbang Kadar Dwifungsi (UU) TNI," Kompas.id, 24 Maret 2025. [Online]. Tersedia: https://www.kompas.id/artikel/menimbang kadar-dwifungsi-uu-tni
H. K. Hoetomo and W. Thukul, "Upaya keluar kandang (barak) oleh TNI: Reformasi yang berputar di tempat?," unpublished, Mar. 2025. [Online],doi: https://doi.org/ 10.13140/RG.2.2.34172.65927.
M. Kumar, L. Khan, and H.-T. Chang, "Evolving techniques in sentiment analysis: a comprehensive review," PeerJ Computer Science, vol. 11, p. e2592, Jan. 2025.
M. S. Hasibuan dan A. Serdano, "Analisis Sentimen Kebijakan Pembelajaran Tatap Muka Menggunakan Support Vector Machine dan Naïve Bayes," Jurnal Riset Sains dan Teknologi, vol. 6, no. 2, pp. 199–204, 2022, doi: https://doi.org/10.30595/jrst.v6i2. 15145.
T. Pratama, R. Nugroho, dan M. Aditya, "Comparison of SVM, Random Forest, and KNN in Sentiment Analysis of Online Learning Policy," International Journal of Educational Data Science, vol. 19, no. 2, pp. 120–135, 2021.
M. Yasir, M. G. Haque, R. Suraji, dan I. Sastrodiharjo, "Analisis Sentimen Terhadap Kontroversi Fatwa MUI Nomor 83 Tahun 2023 Tentang Pemboikotan Produk yang Terafiliasi Israel," Jurnal Ekonomi Manajemen Sistem Informasi, vol. 5, no. 2, pp. 409–422, 2024.
Q. A. Chairunnisa, Y. Herdiyeni, M. K. D. Hardhienata, and J. Adisantoso, "Analisis sentimen pengguna Twitter terhadap program vaksinasi COVID-19 di Indonesia menggunakan algoritme Support Vector Machine," Jurnal Ilmu Komputer dan Agri-Informatika, vol. 9, no. 1, pp. 79–89, 2022.
A, Dendy and T, Sugihartono, "Perbandingan Teknik Optimasi Grid Search dan Randomized Search dalam Meningkatkan Akurasi Metode Klasifikasi SVM," SKANIKA, vol. 8, no. 1, pp. 13–22, 2025
B. Ermawan and N. Cahyono, "Optimasi Metode Klasifikasi Menggunakan FastText dan Grid Search," JIKO, vol. 9, No. 1, pp. 226-238, 2025.
R. M. Pradhana, "Analisis Sentimen Publik terhadap Kebijakan Pemberlakuan Pembatasan Kegiatan Masyarakat Skala Mikro Menggunakan Algoritma Support Vector Machine Studi Kasus Twitter," Doctoral dissertation, Universitas Dinamika, 2021.
M. S. Hasibuan and T. Suhardi, "Analysis of Covid-19 Vaccine Policy Sentiment Using SVM and C4.5," Jurnal Teknik Elektro dan Komputer TRIAC, vol. 9, no. 2, pp. 67–69, 2022.
L. N. Pradany and C. Fatichah, "Analisa Sentimen Kebijakan Pemerintah pada Konten Twitter Berbahasa Indonesia Menggunakan SVM dan K-Medoid Clustering," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer (J-PTIIK), Universitas Brawijaya, vol. 5, no. 10, pp. 3894–3901, 2021.
D. W. Syahputra, B. Rahayudi, and L. Muflikhah, "Analisis Sentimen Twitter terhadap Kebijakan Pemberlakuan Pembatasan Kegiatan Masyarakat menggunakan Metode Support Vector Machine," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer (JPTIIK), vol. 6, no. 4, pp. 1760–1767, 2022. [Online]. Available: http://j-ptiik.ub.ac.id
R. Pebrianto, S. N. Nugraha, A. Latif, and M. R. Firdaus, "Analisis Sentimen Twitter terhadap Menteri Indonesia dengan Algoritma Support Vector Machine dan Naive Bayes," Jurnal Informatika Universitas Pamulang, vol. 17, no. 1, pp. 1–12, 2022.
H. Yaputra and M. R. Muzzaki, "Tagar ‘Indonesia Gelap’ mendapatkan sentimen negatif," Tempo.co, 2023. [Online]. Available: https://www.tempo.co/politik/tagar-indonesia gelap-dapat-81-persen-sentimen-negatif 1221552 [Accessed: Apr. 1, 2025].
Kompas TV, “Syamsu Rizal: Proses Pembahasan RUU TNI Harus Lebih Transparan,” Kompas TV, 2023. [Online]. Available:https://www.kompas.tv/nasional/5810 77/anggota-komisi-i-dpr-fraksi-pkb-ini-akui pembahasan-revisi-uu-tni-kurang-transparan. [Accessed: Apr. 1, 2025].
M. Rahman and R. Fadhil, "Support Vector Machine for Text Classification: A Comprehensive Review," Journal of Artificial Intelligence Research, vol. 45, pp. 112–130, 2021.
D. Suryana and N. Lestari, "Text Preprocessing Techniques for Sentiment Analysis in Social Media Data," Journal of Computer Science and Information Systems, vol. 12, no. 4, pp. 221–238, 2023.
P. Wijaya and T. Prasetyo, "TF-IDF vs. Word Embeddings: Which One is Better for Sentiment Analysis?," in Proc. Int. Conf. Data Science, pp. 33–45, 2022.
R. Hakim and S. Rahman, "Training and Testing Strategies in Machine Learning-Based Sentiment Analysis," International Journal of Artificial Intelligence and Data Mining, vol. 11, no. 2, pp. 87–102, 2024.
B. Santoso, A. Nugraha, and M. Setyawan, "Comparison of Kernel Types in SVM for Sentiment Analysis," Journal of Intelligent Systems and Applications, vol. 9, no. 4, pp. 211-226, 2025.
M. Firdaus and A. Ramadhan, "Evaluating Sentiment Classification Models: Metrics and Best Practices," Journal of Data Science and Machine Learning, vol. 13, no. 1, pp. 45–61, 2023.
T. Nugroho, F. Mahendra, and D. Satria, "Application of Sentiment Analysis for Public Policy Decision Making," International Journal of Government and Technology Studies, vol. 8, no. 3, pp. 190–204, 2025.
How To Cite This :
Refbacks
- There are currently no refbacks.
