Public Sentiment Analysis on the Performance of the Ministry of Finance for the 2025-2029 Period Using the Support Vector Machine (SVM) Method on Social Media Data X
DOI:
https://doi.org/10.30871/jaic.v10i2.12258Keywords:
Sentiment Analysis, Finance Minister, SVM, TF-IDF, X (Twitter)Abstract
The change in leadership at the Ministry of Finance of the Republic of Indonesia for the 2025–2029 period, marked by the appointment of Purbaya Yudhi Sadewa as Minister of Finance, triggered various responses from the public, many of which were recorded on social media. This study aims to examine public sentiment trends regarding the performance of the Ministry of Finance and assess the ability of the Support Vector Machine (SVM) algorithm to classify public opinion. The research data was obtained from the X platform (formerly Twitter) between September and November 2025 and produced 1,164 documents that were declared valid after undergoing preprocessing. Feature extraction was performed using the Term Frequency–Inverse Document Frequency (TF-IDF) method, while the SVM model was optimized with a linear kernel through hyperparameter adjustment. The novelty of this study lies in its comprehensive analysis of sentiment polarity during the early transition phase of fiscal authority in the post–Sri Mulyani era, as well as in testing the robustness of the SVM model in handling ambiguity of economic terminology within X social media data. Through hyperparameter optimization and the integration of TF-IDF weighting, this research further explores how key fiscal policy terms such as taxation and national debt contribute to classification accuracy within the context of political opinion discourse. The analysis results show that negative sentiment dominated with a percentage of 81.1%, mainly related to issues of fiscal policy, taxation, and national debt. On the other hand, positive sentiment was recorded at 18.9% and reflected support and confidence in the new fiscal leadership. The best SVM model with regularization parameter C = 5.0 achieved an accuracy value of 86.27%, an F1-score of 0.86, and an Area Under the Curve (AUC) value of 0.91. These findings confirm that SVM is effective in sentiment classification under naturally imbalanced social media data and offer empirical observations about digital public perception relevant to the evaluation of government fiscal policy communication.
Downloads
References
[1] Mr. Pratama Srg Sistem Informasi and S. Kaputama, “Analisis Sentimen Pada Media Sosial Twitter Terhadap Penegakan Hukum Di Indonesia Tahun 2024 Menggunakan Metode Support Vector Machine (SVM).” [Online]. Available: https://journaledutech.com/index.php/great
[2] L. Rohmatun and A. Baita, “Machine Learning-Based Sentiment Analysis on Twitter (X): A Case Study of the ‘Kabur Aja Dulu’ Issue Using SVM,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[3] D. W. Syahputra, B. Rahayudi, and L. Muflikhah, “Analisis Sentimen Twitter terhadap Kebijakan Pemberlakuan Pembatasan Kegiatan Masyarakat menggunakan Metode Support Vector Machine,” 2022. [Online]. Available: http://j-ptiik.ub.ac.id`
[4] R. N. Mauliza and Y. R. Sipayung, “Penerapan Text Mining Dalam Menganalisis Pendapat Masyarakat Terhadap Pemilu 2024 Pada Media Sosial X Menggunakan Metode Naive Bayes,” Technomedia Journal, vol. 9, no. 1, pp. 1–16, Feb. 2024, doi: 10.33050/tmj.v9i1.2212.
[5] M. Rizki Maulana and R. A. Putri, “Sistemasi: Jurnal Sistem Informasi Analisis Sentimen terhadap Komisi Pemilihan Umum 2024 di Indonesia melalui Twiter menggunakan Algoritma Support Vector Machine (SVM) Sentiment Analysis of the 2024 General Election Commission in Indonesia through Twiter using the Support Vector Machine (SVM) Algorithm.” [Online]. Available: http://sistemasi.ftik.unisi.ac.id
[6] F. Fatkhurrohman, B. I. Nugroho, and N. Fadillah, “Analisis Sentimen Program Makan Bergizi Gratis Pemerintah RI Melalui Twitter Menggunakan Metode SVM,” RIGGS: Journal of Artificial Intelligence and Digital Business, vol. 4, no. 3, pp. 3906–3917, Aug. 2025, doi: 10.31004/riggs.v4i3.2533.
[7] P. T. Sejati, F. Al Zami, A. Marjuni, H. Indrayani, and I. D. Puspitarini, “Aspect-Based Sentiment Analysis for Enhanced Understanding of ‘Kemenkeu’ Tweets,” 2024. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[8] S. Berliani and S. Lestari, “Analisis Sentimen Masyarakat Terhadap Isu Pecat Sri Mulyani Pada Twitter Menggunakan Metode Naive Bayes Dan Support Vector Machine,” Jurnal Sains dan Teknologi, vol. 5, no. 3, pp. 951–960, Apr. 2024, doi: 10.55338/saintek.v5i3.2746.
[9] S. Ramadhani Putri et al., “Sistemasi: Jurnal Sistem Informasi Analisis Sentimen Publik terhadap Nadiem Makarim sebagai Mendikbudrisktek menggunakan Support Vector Machine (SVM).” [Online]. Available: http://sistemasi.ftik.unisi.ac.id
[10] A. A. Purnama and Y. R. Sipayung, “Sentiment Analysis of Public Service Using Naïve Bayes Classifier,” Journal of Information Systems and Informatics, vol. 7, no. 3, pp. 2439–2457, Sep. 2025, doi: 10.51519/journalisi.v7i3.1207.
[11] A. Dian Oktavianingsih, A. Fadlil Fauzi, J. Immanuel, O. DSimatupang, F. Amsury, and R. Fahlapi, “Analisis Sentimen Komentar YouTube terhadap Pengangkatan Menkeu Purbaya Menggunakan Algoritma SVM dan Naïve Bayes,” Jurnal Cendekia Ilmiah, vol. 5, no. 1, 2025.
[12] M. A. Gumilang, F. Abdillah, M. Y. Amin, and M. Hasan, “Sentiment Analysis of Indonesian Ministries Social Media: Citizen Responses Utilizing TextBlob Analyser,” Jurnal Sosioteknologi, vol. 23, no. 2, pp. 203–216, Aug. 2024, doi: 10.5614/sostek.itbj.2024.23.2.5.
[13] 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,” vol. 17, pp. 1–12, 2022.
[14] G. Forda Nama, A. H. Shalihah, B. Wintoro, Y. Mulyani, and D. Despa, “Implementation of Naïve Bayes Classifier & Support Vector Machine Algorithm for Sentiment Classification using Twitter Data on Indonesian Presidential Candidates In 2024,” 2024. [Online]. Available: https://www.jisem-journal.com/
[15] A. Sentimen et al., “Analisis Sentimen Masyarakat Di Media Sosial X Terhadap Kemenkes Dengan Naive Bayes dan SVM,” Jurnal Sains dan Teknologi, vol. 7, no. 1, pp. 1–6, 2025, doi: 10.55338/saintek.v7i1.4615.
[16] A. M. AlHakim, P. D. Atika, and H. Herlawati, “Analisis Sentimen Masyarakat Terhadap PHK di Indonesia Pada Twitter Menggunakan Naïve Bayes dan Support Vector Machine (SVM),” Journal of Students‘ Research in Computer Science, vol. 6, no. 1, pp. 113–124, May 2025, doi: 10.31599/96sfw544.
[17] D. Shinta Angreni, S. Khaerawati Nur, and D. Luvi Jayanto, “Sentiment Analysis for the 2024 DKI Jakarta Gubernatorial Election Using a Support Vector Machine Approach,” 2025. [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[18] D. Fajar Fiandaru and Y. Romando Sipayung, “ELSE (Elementary School Education Journal) Penerapan Metode Klasifikasi Naive Bayes untuk Analisis Sentimen terhadap Undang-Undang ITE di Media Sosial Twitter,” 2025, [Online]. Available: https://journal.um-surabaya.ac.id/index.php/pgsd
[19] A. K. Author, “Analisis Sentimen Di Instagram Terhadap Menteri Keuangan Purbaya Yudhi Sadewa Menggunakan Metode Logistic Regression,” Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 3S1, Oct. 2025, doi: 10.23960/jitet.v13i3S1.8002.
[20] A. Irianti, H. Halimah, S. Sutedi, and M. Agariana, “Integration of BERT and SVM in Sentiment Analysis of Twitter/X Regarding Constitutional Court Decision No. 60/PUU-XXII/2024,” Jurnal Teknik Informatika (Jutif), vol. 6, no. 2, pp. 469–482, Apr. 2025, doi: 10.52436/1.jutif.2025.6.2.4068.
[21] I. Prayugah, U. Indahyanti, and N. Ariyanti, “Analisis Sentimen Publik Atas Respons Pemerintah Pada Serangan Ransomware Dengan Pendekatan Machine Learning Dan Smote,” JOISIE (Journal Of Information Systems And Informatics Engineering), vol. 8, no. 2, p. 333, Jan. 2025, doi: 10.35145/joisie.v8i2.4764.
[22] J. Br Sitepu, S. Ramadani, M. Khadapi, S. Informasi, and S. Kaputama, “Analisis Sentimen Pengguna Media Twitter Terhadap Kurikulum Merdeka Menggunakan Algoritma Support Vector Machine (SVM).” [Online]. Available: https://journaledutech.com/index.php/great
[23] T. Saputro and A. Hermawan, “Comparison of Naive Bayes and Support Vector Machine in Sentiment Analysis of Siwaslu Application,” bit-Tech, vol. 8, no. 2, pp. 2004–2015, Dec. 2025, doi: 10.32877/bt.v8i2.3184.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Annisa Tyas Wahyu Setyaningsih; Yoannes Romando Sipayung
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).
