Event-Based Detection of Provocative Political Discourse on Indonesian Twitter: A Comparative Study of SVM and IndoBERT

Authors

  • Evril Fadrekha Cahyani Indonesia
  • Ali Nur Ikhsan Indonesia
  • Deuis Nur Astrida Indonesia
Pages Icon

DOI:

https://doi.org/10.63158/journalisi.v8i1.1409

Keywords:

Provocative discourse, Political polarization, IndoBERT, Support Vector Machine, Event-based Twitter analysis

Abstract

Political polarization on Indonesian social media intensified during the August 2025 House of Representatives (DPR) demonstrations, where provocative and sarcastic tweets helped amplify institutional criticism and widen public conflict. This study examines event-based automatic detection of provocative political discourse by comparing a feature-based Support Vector Machine (SVM) classifier with a transformer-based IndoBERT model on a large-scale Indonesian Twitter (X) corpus collected from 15 August to 15 September 2025. Tweets were preprocessed and labeled using a rule-based proxy lexicon to distinguish provocative from neutral content, then both models were trained and evaluated under the same experimental setting. Results show that SVM is highly effective for recognizing explicit provocation expressed through repetitive and lexically salient slogans, whereas IndoBERT provides more stable detection of implicit and context-dependent provocation, including irony and sarcasm that are common in Indonesian political talk online. In addition, temporal exploration indicates sharp spikes in tweet volume that align with key offline protest moments, suggesting a close coupling between street-level mobilization and digital discourse dynamics. Overall, the findings support the use of contextual NLP models within event-centered social media analysis to strengthen scalable monitoring of polarization and to inform early-warning approaches for escalating conflict in Indonesia’s digital public sphere.

Downloads

Download data is not yet available.

References

[1] S. Gayatri and I. B. C. Satwika, “The Role of Social Media as a Medium for Political Information (Peran Media Sosial sebagai Media Sarana Informasi Politik),” Anubhava: J. Ilmu Komun. Hindu, vol. 2, no. 1, pp. 273–282, May 2022, doi: 10.25078/anubhava.v2i1.1050.

[2] L. Judijanto, R. Maulinda, S. Zulaika, I. Tjahyadi, and S. Suroso, “The Influence of Information Sources and Social Interaction on Social Media toward the Formation of Public Political Opinion in Indonesia (Pengaruh Sumber Informasi dan Interaksi Sosial di Media Sosial terhadap Pembentukan Opini Politik Masyarakat di Indonesia),” Sanskara Ilmu Sos. Humaniora, vol. 1, no. 01, pp. 21–31, Dec. 2023, doi: 10.58812/sish.v1i01.303.

[3] A. Arpandi, “Online Media in Increasing Public Political Participation in General Elections (Media Online dalam Meningkatkan Partisipasi Politik Masyarakat pada Pemilihan Umum (Pemilu)),” Edu Soc.: J. Pendidik. Ilmu Sos. Pengabdi. Masy., vol. 3, no. 1, pp. 843–855, Aug. 2023, doi: 10.56832/edu.v3i1.293.

[4] A. A. Santoso, “The Nomination of Ganjar Pranowo as Presidential Candidate: Topic Analysis Study on Reverse Agenda Setting Related to the Ganjar Pranowo Case (Penetapan Ganjar Pranowo Sebagai Calon Presiden: Studi Analisis Topik pada Reverse Agenda Setting Terkait Kasus Ganjar Pranowo),” J. Ilm. Ilmu Pendidik., vol. 7, no. 4, pp. 3805–3812, Apr. 2024, doi: 10.54371/jiip.v7i4.4140.

[5] A. C. Rosdiana and A. A. Suryaningtyas, “Identity Politics in Ganjar Pranowo’s Political Campaign Ahead of the 2024 Presidential Election (Politik Identitas dalam Kampanye Politik Ganjar Pranowo Menjelang Pilpres 2024),” J. Audiens, vol. 5, no. 1, pp. 77–90, Mar. 2024, doi: 10.18196/jas.v5i1.336.

[6] A. Bilbao-Jayo and A. Almeida, “Improving Political Discourse Analysis on Twitter With Context Analysis,” IEEE Access, vol. 9, pp. 104846–104863, 2021, doi: 10.1109/ACCESS.2021.3099093.

[7] M. Dynel, “Do We Know Whether to Laugh or Cry? User Responses to @Ukraine’s Dark-humour Meme,” J. Creative Commun., vol. 19, no. 3, pp. 243–258, Nov. 2024, doi: 10.1177/09732586241239908.

[8] P. Kanungo and H. Singh, “A Feature Extraction based Improved Sentiment Analysis on Apache Spark for Real-time Twitter Data,” Scalable Comput.: Pract. Exp., vol. 24, no. 4, pp. 847–855, Nov. 2023, doi: 10.12694/scpe.v24i4.2343.

[9] H. Setyawan, L. M. Azizah, and A. Y. Pradani, “Sentiment Analysis of Public Responses on Indonesia Government Using Naïve Bayes and Support Vector Machine,” Emerg. Inf. Sci. Technol., vol. 4, no. 1, pp. 1–7, May 2023, doi: 10.18196/eist.v4i1.18681.

[10] A. R. W. Sait and M. K. Ishak, “Deep Learning with Natural Language Processing Enabled Sentimental Analysis on Sarcasm Classification,” Comput. Syst. Sci. Eng., vol. 44, no. 3, pp. 2553–2567, 2023, doi: 10.32604/csse.2023.029603.

[11] H. Jayadianti et al., “Sentiment analysis of Indonesian reviews using fine-tuning IndoBERT and R-CNN,” ILKOM J. Ilm., vol. 14, no. 3, pp. 348–354, Dec. 2022, doi: 10.33096/ilkom.v14i3.1505.348-354.

[12] D. I. Putri et al., “IndoBERT Model Analysis: Twitter Sentiments on Indonesia’s 2024 Presidential Election,” J. Appl. Inform. Comput., vol. 8, no. 1, pp. 7–12, Jul. 2024, doi: 10.30871/jaic.v8i1.7440.

[13] O. H. Rahman, G. Abdillah, and A. Komarudin, “Classification of Hate Speech on Twitter Social Media Using Support Vector Machine (Klasifikasi Ujaran Kebencian pada Media Sosial Twitter Menggunakan Support Vector Machine),” J. RESTI, vol. 5, no. 1, pp. 17–23, Feb. 2021, doi: 10.29207/resti.v5i1.2700.

[14] M. Miqdad, “Literature Review: Political Buzzers and Opinion Development on Social Media in Indonesia (Literature Review: Buzzer Politik dan Pengembangan Opini di Media Sosial di Indonesia),” NeoRespublica: J. Ilmu Pemerintah., vol. 5, no. 2, pp. 689–698, Mar. 2024, doi: 10.52423/neores.v5i2.231.

[15] R. A. Saputra and Y. Sibaroni, “Multilabel Hate Speech Classification in Indonesian Political Discourse on X using Combined Deep Learning Models with Considering Sentence Length,” J. Ilmu Komput. Inform., vol. 18, no. 1, pp. 113–125, Feb. 2025, doi: 10.21609/jiki.v18i1.1440.

[16] N. N. A. Aryanti and O. Suria, “Sentiment Analysis of Layoffs in Indonesia: Comparison of IndoBERT with SVM, Random Forest, and Decision Tree with TF-IDF Optimization (Analisis Sentimen terhadap Pemutusan Hubungan Kerja di Indonesia: Komparasi IndoBERT dengan SVM, Random Forest, dan Decision Tree dengan Optimasi TF-IDF),” Rabit: J. Teknol. Sist. Inf. Univrab, vol. 10, no. 2, pp. 1158–1176, Jul. 2025, doi: 10.36341/rabit.v10i2.6364.

[17] I. Riadi, A. Fadlil, and U. A. Dahlan Yogyakarta, “Identifying Hate Speech in Tweets with Sentiment Analysis on Indonesian Twitter Utilizing Support Vector Machine Algorithm,” 2023.

[18] S. Kumar et al., “An anatomical comparison of fake-news and trusted-news sharing pattern on Twitter,” Comput. Math. Organ. Theory, vol. 27, no. 2, pp. 109–133, Jun. 2021, doi: 10.1007/s10588-019-09305-5.

[19] T. Lynn et al., “An Exploratory Data Analysis of the #Crowdfunding Network on Twitter,” J. Open Innov.: Technol. Mark. Complex., vol. 6, no. 3, p. 80, Sep. 2020, doi: 10.3390/joitmc6030080.

[20] B. Wilie et al., “IndoNLU: Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” in Proc. AACL-IJCNLP 2020, Suzhou, China, 2020, pp. 843–857.

[21] F. Koto, A. Rahimi, J. H. Lau, and T. Baldwin, “IndoLEM and IndoBERT: A Benchmark Dataset and Pre-trained Language Model for Indonesian NLP,” in Proc. COLING 2020, Barcelona, Spain, 2020, pp. 757–770.

[22] A. W. Pradana and M. Hayaty, “The Effect of Stemming and Removal of Stopwords on the Accuracy of Sentiment Analysis on Indonesian-language Texts,” Kinetik, vol. 4, no. 4, pp. 375–380, Oct. 2019, doi: 10.22219/kinetik.v4i4.912.

[23] N. H. Jeremy, “The Impact of Text Preprocessing in Sarcasm Detection on Indonesian Social Media Contents,” J. EMACS (Eng. Math. Comput. Sci.), vol. 7, no. 2, pp. 183–189, 2025, doi: 10.21512/emacsjournal.v6.

[24] E. W. Pamungkas et al., “Enhancing hate speech detection in Indonesian using abusive words lexicon,” Indones. J. Electr. Eng. Comput. Sci., vol. 33, no. 1, p. 450, Jan. 2024, doi: 10.11591/ijeecs.v33.i1.pp450-462.

[25] V. B. Lestari and C. A. Hutagalung, “Evaluation of TF-IDF Extraction Techniques in Sentiment Analysis of Indonesian-Language Marketplaces Using SVM, Logistic Regression, and Naive Bayes,” J-KOMA J. Comput. Sci. Appl., 2025, doi: 10.21009/j.

[26] R. Santosa, A. B. Nusantara, and S. Imron, “Comparative Analysis of SVM and IndoBERT for Intent Classification in Indonesian Overtime Chatbots,” J. Syst. Comput. Eng. (JSCE), vol. 6, no. 3, pp. 258–270, Aug. 2025, doi: 10.61628/jsce.v6i3.2058.

[27] R. Romindo, J. J. Pangaribuan, and O. P. Barus, “Implementation of TF-IDF and Support Vector Machine Algorithms for Detecting Cyberbullying Comments on TikTok Social Media (Implementasi Algoritma TF-IDF dan Support Vector Machine terhadap Analisis Pendeteksi Komentar Cyberbullying di Media Sosial TikTok),” J. Device, vol. 13, no. 1, pp. 124–134, 2023.

[28] F. Baharuddin and M. F. Naufal, “Fine-Tuning IndoBERT for Indonesian Exam Question Classification Based on Bloom’s Taxonomy,” J. Inf. Syst. Eng. Bus. Intell., vol. 9, no. 2, pp. 253–263, Oct. 2023, doi: 10.20473/jisebi.9.2.253-263.

[29] A. R. Hanum et al., “Performance Analysis of BERT Text Classification Algorithm in Detecting Hoax News (Analisis Kinerja Algoritma Klasifikasi Teks BERT dalam Mendeteksi Berita Hoaks),” J. Teknol. Inf. Ilmu Komput., vol. 11, no. 3, pp. 537–546, 2024, doi: 10.25126/jtiik2024118093.

Downloads

Published

2026-02-24

Issue

Vol. 8 No. 1 (2026): February

Section

Articles

License

Copyright (c) 2026 Journal of Information Systems and Informatics

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Authors Declaration

  1. The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
  2. The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
  3. The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
  4. The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
  5. The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
  6. The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
  7. If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
  8. The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights

How to Cite

[1]
E. F. Cahyani, A. N. Ikhsan, and D. N. Astrida, “Event-Based Detection of Provocative Political Discourse on Indonesian Twitter: A Comparative Study of SVM and IndoBERT”, journalisi, vol. 8, no. 1, pp. 530–548, Feb. 2026, doi: 10.63158/journalisi.v8i1.1409.