Sentiment Analysis of YouTube Comments on the 2025 DPR RI Demonstration Using Machine Learning
DOI:
https://doi.org/10.30871/jaic.v10i2.12254Keywords:
DPR RI Demonstration, Machine Learning, Sentiment Classification, Text Classification, Youtube CommentAbstract
The 2025 DPR RI Demonstration is a national political issue that has triggered a broad response from the Indonesian public, especially through user comments on the YouTube platform. These comments reflect diverse and emotional public opinion, making it relevant to study using a Machine Learning based Sentiment Analysis approach. This study aims to compare the performance of the Support Vector Machine (SVM), Multilayer Perceptron (MLP) based Neural Network (NN), and Random Forest algorithms in classifying YouTube comment sentiments related to the 2025 DPR RI Demonstration issue. Data were obtained through a comment collection process, then processed through text preprocessing and feature weighting stages using the TF-IDF method. The data used in this study were publicly accessible comments, and no personally identifiable information was collected or disclosed to ensure user privacy and ethical data use. Model performance evaluation was conducted using a confusion matrix with accuracy, precision, recall, and F1-score metrics. The results indicate that the SVM algorithm achieved the best performance, with weighted average accuracy, precision, recall, and F1-score values of 96.20%, respectively. Meanwhile, the Neural Network achieved accuracy, precision, recall, and F1-score values of 95.90%. Random Forest produced an accuracy of 88.40%, precision of 88.60%, recall of 88.40%, and an F1-score of 88.50%. These findings indicate that SVM is more effective in handling the complexity of language in comments related to political issues compared to the other two algorithms. The results of this study are expected to be a reference in selecting the right algorithm for analyzing political issue sentiment on social media.
Downloads
References
[1] I. Koswara, “Diskursus Digital dan Suara Publik: Komentar YouTube dalam Kasus #IndonesiaGelap,” Glob. Komunika, vol. 8, no. 2, 2025.
[2] D. Röchert, G. Neubaum, and S. Stieglitz, “Identifying Political Sentiments on YouTube: A Systematic Comparison Regarding the Accuracy of Recurrent Neural Network and Machine Learning Models,” Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 12259 LNCS, pp. 107–121, 2020, doi: 10.1007/978-3-030-61841-4_8.
[3] A. N. Syafia, M. F. Hidayattullah, and W. Suteddy, “Studi Komparasi Algoritma SVM Dan Random Forest Pada Analisis Sentimen Komentar Youtube BTS,” J. Inform. J. Pengemb. IT, vol. 8, no. 3, pp. 207–212, 2023, doi: 10.30591/jpit.v8i3.5064.
[4] I. Via Mariska, A. Meiriza, and D. Lestarini, “Comparison of Support Vector Machine and Random Forest Algorithms in Sentiment Analysis of the JMO Mobile Application,” J. Appl. Informatics Comput., vol. 9, no. 5, pp. 2533–2540, 2025, doi: 10.30871/jaic.v9i5.10764.
[5] O. N. Akande, J. Ayoola, S. Misra, R. Ahuja, A. Agrawal, and J. Oluranti, “Application of Support Vector Machine and Convolutional Neural Network for Sentence-Level Sentiment Analysis of Companies Products Review,” Lect. Notes Electr. Eng., vol. 881, pp. 133–145, 2022, doi: 10.1007/978-981-19-1111-8_12.
[6] R. Uma, H. Aafreen Sana, P. Jawahar, and B. V. Rishitha, “Support Vector Machine and Convolutional Neural Network Approach to Customer Review Sentiment Analysis,” 2022 1st Int. Conf. Comput. Sci. Technol. ICCST 2022 - Proc., pp. 239–243, 2022, doi: 10.1109/ICCST55948.2022.10040381.
[7] X. Fan, J. Zhang, and M. Yang, “a Sentiment Analysis Model for Electroencephalogram Signals of Students in Universities Using a Convolutional Neural Network and Support Vector Machine Models,” J. Mech. Med. Biol., vol. 23, no. 9, pp. 1–15, 2023, doi: 10.1142/S0219519423400869.
[8] S. Khomsah, “Sentiment Analysis On YouTube Comments Using Word2Vec and Random Forest,” Telematika, vol. 18, no. 1, p. 61, 2021, doi: 10.31315/telematika.v18i1.4493.
[9] N. Rochmawati, A. K. Zyen, and N. A. Widiastuti, “Comparison of Support Vector Machine (SVM) and Random Forest Algorithms in the Analysis of SOcial Media X User Sentiment Towards the TNI Bill,” J. Appl. Informatics Comput., vol. 9, no. 5, pp. 2854–2860, 2025, doi: 10.30871/jaic.v9i5.10883.
[10] N. Shivsharan, V. Kambli, S. Dabholkar, A. Dalvi, and T. Sukali, “Evaluating Machine Learning Models for Sentiment Analysis of YouTube Comments and Creating an Accessible Web Application for Comment Analysis,” Procedia Comput. Sci., vol. 258, pp. 3165–3174, 2025, doi: 10.1016/j.procs.2025.04.574.
[11] Fenilinas Adi Artanto, “Analisis Sentimen Opini Publik terhadap Fenomena Bunuh Diri Mahasiswa di Twitter Menggunakan Algoritma Naive Bayes,” SATESI J. Sains Teknol. dan Sist. Inf., vol. 4, no. 1, pp. 70–77, 2024, doi: 10.54259/satesi.v4i1.2908.
[12] H. S. Dutta and B. Khan, “YTCommentVerse: A Multi-Category Multi-Lingual YouTube Comment Corpus,” CIKM 2025 - Proc. 34th ACM Int. Conf. Inf. Knowl. Manag., no. December, pp. 6351–6355, 2025, doi: 10.1145/3746252.3761629.
[13] K. E. V Sihombing, M. A. I. Pakereng, U. Kristen, and S. Wacana, “Wawancara Presiden Prabowo Menggunakan Machine,” vol. 4, no. 4, pp. 327–336, 2025.
[14] A. M. Van Der Veen and E. Bleich, “The advantages of lexicon-based sentiment analysis in an age of machine learning,” PLoS One, vol. 20, no. 1 January, pp. 1–19, 2025, doi: 10.1371/journal.pone.0313092.
[15] Y. Fauziah, B. Yuwono, and A. S. Aribowo, “Lexicon Based Sentiment Analysis in Indonesia Languages : A Systematic Literature Review,” RSF Conf. Ser. Eng. Technol., vol. 1, no. 1, pp. 363–367, 2021, doi: 10.31098/cset.v1i1.397.
[16] Z. Jiang, B. Gao, Y. He, Y. Han, P. Doyle, and Q. Zhu, “Text Classification Using Novel Term Weighting Scheme-Based Improved TF-IDF for Internet Media Reports,” Math. Probl. Eng., vol. 2021, no. ii, 2021, doi: 10.1155/2021/6619088.
[17] B. A. Santoso, I. Nugroho, and D. U. Asyfiya, “TIN: Terapan Informatika Nusantara Perbandingan Algoritma Naïve Bayes, Support Vector Machine, dan Random Forest Untuk Analisis Sentimen Komentar Politik Youtube,” TIN Terap. Inform. Nusant., vol. 6, no. 4, pp. 391–400, 2025, doi: 10.47065/tin.v6i4.8326.
[18] K. M. Sagar, “MultiClass Text Classification Using Support Vector Machine,” Interantional J. Sci. Res. Eng. Manag., vol. 07, no. 12, pp. 1–10, 2023, doi: 10.55041/ijsrem27465.
[19] M. Kerasiotis, L. Ilias, and D. Askounis, “Depression detection in social media posts using transformer-based models and auxiliary features,” Soc. Netw. Anal. Min., vol. 14, no. 1, pp. 1–16, 2024, doi: 10.1007/s13278-024-01360-4.
[20] A. Ahmed Bilal, O. Ayhan Erdem, and S. Toklu, “Children’s Sentiment Analysis from Texts by Using Weight Updated Tuned with Random Forest Classification,” IEEE Access, vol. 12, no. May, pp. 70089–70104, 2024, doi: 10.1109/ACCESS.2024.3400992.
[21] R. Yunita and M. Kamayani, “Perbandingan Algoritma SVM Dan Naïve Bayes Pada Analisis Sentimen Kebijakan Penghapusan Kewajiban Skripsi,” Indones. J. Comput. Sci., vol. 12, no. 5, pp. 2879–2890, 2023.
[22] A. Giachanou, P. Rosso, and F. Crestani, “The impact of emotional signals on credibility assessment,” J. Assoc. Inf. Sci. Technol., vol. 72, no. 9, pp. 1117–1132, 2021, doi: 10.1002/asi.24480.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Adelia Putri Widyasari, Muljono Muljono
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:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement 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 acknowledgement 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 (See The Effect of Open Access).
