114.jpg){kind=logo}
Analisis Sentimen menggunakan Algoritma Machine Learning terhadap Isu Gencatan Senjata Iran-Trump di YouTube
Abstract
Penelitian ini bertujuan untuk mengklasifikasikan sentimen publik di platform YouTube terkait isu gencatan senjata antara Iran dan mantan Presiden Amerika Serikat, Donald Trump. Dataset yang diambil dari komentar YouTube berjumlah 2000 dianalisis dan menghasilkan 576 data uji dengan distribusi sentimen yang tidak seimbang, pelabelan dataset menggunakan RoBERTa dengan 2 (dua) kelas, yaitu 428 label negatif, 114 netral, dan 34 positif. Ekstraksi fitur menggunakan pendekatan Bag-of-Words kombinasi unigram dan bigram untuk melatih algoritma machine learning, dengan fokus pada komparasi Support Vector Machine (SVM) dan Naïve Bayes. Hasil pengujian secara numerik menunjukkan bahwa Naïve Bayes memperoleh akurasi lebih tinggi sebesar 78.6% dengan skor macro F1 sebesar 0.503 akibat bias pada kelas mayoritas, sedangkan untuk SVM menghasilkan akurasi sebesar 74% dengan macro F1 mencapai 0.539. Penelitian ini berhasil mengimplementasikan model dengan baik meskipun Naïve Bayes unggul dalam akurasi umum karena dominasi data bersentimen negatif, SVM terbukti lebih seimbang dalam memetakan polarisasi sentimen publik yang kompleks di media sosial.
Keywords
Full Text:
PDFReferences
Aftab, F., Bazai, S. U., Marjan, S., Baloch, L., Aslam, S., Amphawan, A., & Neo, T. K. (2023). A Comprehensive Survey on Sentiment Analysis Techniques. International Journal of Technology, 14(6), 1288–1298. https://doi.org/10.14716/IJTECH.V14I6.6632
Arsi, P., Kusuma, B. A., & Nurhakim, A. (2021). Analisis Sentimen Pindah Ibu Kota Berbasis Naive Bayes Classifier. Jurnal Informatika Upgris, 7(1). https://doi.org/10.26877/JIU.V7I1.7636
Iedwan, A. S., Mauliza, N., Pristyanto, Y., Hartanto, A. D., & Rohman, A. N. (2024). Comparative Performance of SVM and Multinomial Naïve Bayes in Sentiment Analysis of the Film “Dirty Vote.” Scientific Journal of Informatics, 11(3), 839–848. https://doi.org/10.15294/sji.v11i3.10290
Jamil, M., Hadiyanto, H., & Sanjaya, R. (2024). Sentiment Analysis: Classifying Public Comments on YouTube in Disaster Management Simulation in Indonesia Using Naïve Bayes and Support Vector Machine. Ingenierie Des Systemes d’Information, 29(2), 437–446. https://doi.org/10.18280/ISI.290205
Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., Stoyanov, V., & Allen, P. G. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. https://arxiv.org/pdf/1907.11692
Mahfudza, N., & Ihksan, M. (2025). Sentiment Analysis of Youtube Comments on Indonesian Presidential Candidates in 2024 using Naïve Bayes Classifier. JURIKOM (Jurnal Riset Komputer), 12(2), 140–148. https://doi.org/10.30865/jurikom.v12i2.8538
Mehta, T., & Deshmukh, G. (2022). YouTube Ad View Sentiment Analysis using Deep Learning and Machine Learning. International Journal of Computer Applications, 184(11), 10–14. https://doi.org/10.5120/ijca2022922078
Moro, S., & Rita, P. (2022). Data and text mining from online reviews: An automatic literature analysis. In Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery (Vol. 12, Number 3). John Wiley and Sons Inc. https://doi.org/10.1002/widm.1448
Muhammad Mutawakkil Alallah, Mokhammad Amin Hariyadi, Triyo Supriyatno, & Riana, E. (2026). Implementasi BERT dan IndoRoBERTa untuk Klasifikasi Sentimen Opini Publik tentang Kecerdasan Buatan dalam Pendidikan di YouTube. JURIKOM (Jurnal Riset Komputer), 13(2), 666–678. https://doi.org/10.30865/jurikom.v13i2.9697
Nur, A., Saputra, A., Saputro, R. E., & Saputra, S. (2025). Enhancing Sentiment Analysis Accuracy Using SVM and Slang Word Normalization on YouTube Comments. Sinkron : Jurnal Dan Penelitian Teknik Informatika, 9(2), 687–699. https://doi.org/10.33395/SINKRON.V9I2.14613
Rahman, A., Rahmat, F., Fariqi, M. Y., & Adi, S. (2020). Naive Bayes Method to Analyze Sentiment Accuracy on YouTube Comments. Jurnal EECCIS (Electrics, Electronics, Communications, Controls, Informatics, Systems), 14(1), 31–34. https://doi.org/10.21776/JEECCIS.V14I1.627
Rajesh Kanna, P., & Santhi, P. (2021). Unified Deep Learning approach for Efficient Intrusion Detection System using Integrated Spatial–Temporal Features. Knowledge-Based Systems, 226, 107132. https://doi.org/10.1016/J.KNOSYS.2021.107132
Susanti, E., Maimunah, M., & Nugroho, S. (2025). Sentiment Analysis of YouTube Comments Using Machine Learning Models. PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic, 13(1), 103–114. https://doi.org/10.33558/PIKSEL.V13I1.10743
Wankhade, M., Rao, A. C. S., & Kulkarni, C. (2022). A survey on sentiment analysis methods, applications, and challenges. Artificial Intelligence Review, 55(7), 5731–5780. https://doi.org/10.1007/s10462-022-10144-1
Yadav, J. (2023). Sentiment Analysis on Social Media. https://doi.org/10.32388/YF9X04
DOI: https://doi.org/10.46576/device.v7i1.9042
Article Metrics
Abstract view : 0 timesPDF – 0 times
Refbacks
- There are currently no refbacks.
Copyright (c) 2026 Yeremia Agung Chandra
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY
Terindeks pada:
Member Of :
DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY
Published by :FAKULTAS TEKNIK DAN ILMU KOMPUTER
PROGRAM STUDI SISTEM INFORMASI
UNIVERSITAS DHARMAWANGSA
Alamat : Jl. K. L. Yos Sudarso No. 224 Medan
Kontak : Tel. 061 6635682 - 6613783 Fax. 061 6615190
E-mail : admin_device@dharmawangsa.ac.id
Device : Journal Of Information System, Computer Science And Information Technology by Universitas Dharmawangsa is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Based on a work at http://jurnal.dharmawangsa.ac.id/index.php/device