Analisis Komparatif Sentimen Publik terhadap Liputan Media Terkait Aksi Menteri Keuangan Menggunakan Algoritma SVM dan RoBERTa

Budi Santosa; Kardita Magda; Ega Budiman; Ryan Randy Suryono

doi:10.55681/sentri.v5i2.5858

Authors

Budi Santosa Universitas Teknokrat Indonesia
Kardita Magda Universitas Teknokrat Indonesia
Ega Budiman Universitas Teknokrat Indonesia
Ryan Randy Suryono Universitas Teknokrat Indonesia

DOI:

https://doi.org/10.55681/sentri.v5i2.5858

Keywords:

Sentiment Analysis, SVM, RoBERTa, YouTube Comments, Finance Minister

Abstract

Public opinion on social media is a crucial representation of government policy legitimacy, especially in the fiscal sector. This study intends to provide a comparative investigation of the efficacy of sentiment categorization on YouTube comments pertaining to the activities of the Indonesian Finance Minister by juxtaposing the Support Vector Machine (SVM) algorithm with the RoBERTa Transformer model. A total of 3,780 comments were acquired from national digital media channels. The research method involves intensive text preprocessing, including stemming using the Sastrawi algorithm and lexicon-based labeling. The results showed that the SVM algorithm with TF-IDF features achieved an accuracy of 83.33% and an F1-score of 76.05%. In contrast, the RoBERTa model showed a significantly lower performance with an accuracy of 29.76%. This study concludes that for datasets dominated by neutral sentiments and informal language in specific Indonesian contexts, traditional machine learning like SVM with optimal feature engineering remains more reliable and efficient than complex Transformer models that require more extensive fine-tuning.

Downloads

Download data is not yet available.

References

Agresia, V., Suryono, R. R., Indonesia, U. T., Ratu, L., & Lampung, K. B. (2025). COMPARISON OF SVM , NAÏVE BAYES , AND LOGISTIC REGRESSION ALGORITHMS FOR SENTIMENT ANALYSIS OF FRAUD AND BOTS IN PURCHASING CONCERT TICKET KOMPARASI ALGORITMA SVM , NAÏVE BAYES , DAN LOGISTIC REGRESSION UNTUK ANALISIS SENTIME.

Agustianto, B., Musyafa, A., & Waskita, A. A. (2025). Analisis Sentimen Publik Terhadap Enterprise Resource Planning ( ERP ) Di Media Sosial X Menggunakan Model Roberta Dan Twitbert. 8(2), 142–152.

Alita, D., Indonesia, U. T., Classifier, N. B., Machine, V., & Mining, T. (2023). Sentimen Analisis Vaksin Covid-19 Menggunakan Naive Bayes Dan Support Vector Machine. 1(1), 1–12.

Apriansyah, F. M., Ramadhan, T. I., Hidayat, C. R., & Karta, A. (2025). Perbandingan IndoBERT dan IndoRoBERTa Untuk Analisis Sentimen Pada Film Dokumenter Dirty Vote. 10(3), 593–605. https://doi.org/10.30591/jpit.v10i3.8607

Fauzi, M. A. (2019). Word2Vec model for sentiment analysis of product reviews in Indonesian language. 9(1), 525–530. https://doi.org/10.11591/ijece.v9i1.pp525-530

Haliza, D., & Ikhsan, M. (2025). Sentiment Analysis on Public Perception of the Nusantara Capital on Social Media X Using Support Vector Machine ( SVM ) and K-Nearest Neighbor ( K-NN ) Methods. 9(3), 716–723.

Kamila, S. A., Wahda, A. W., Febriati, B. N., & Yudhianto, R. B. (2025). AUGMENTASI GPT-4O DAN FINE-TUNING INDOBERT UNTUK ANALISIS SENTIMEN PUBLIK PADA ISU RESHUFFLE MENTERI KEUANGAN. 10(2), 1–17.

Khaidar, A., & Kurnia, S. (2025). Intelligent Sentiment Mapping on Instagram for Finance Minister Purbaya Yudhi Sadewa Based on Logistic Regression. 5(1).

Kusuma, A., & Nugroho, A. (2021). Analisa Sentimen Pada Twitter Terhadap Kenaikan Tarif Dasar Listrik Dengan Metode Naïve Bayes. 15(2), 137–146.

Pramesti, R. F. (2025). ANALISIS EFISIENSI APBN ERA PRABOWO : KAJIAN EKONOMI DAN ANALISIS SENTIMEN PUBLIK. 8(2), 1147–1161.

Putri, I., & Lestari, M. T. (2024). ANALISIS SENTIMEN OPINI PUBLIK TERHADAP LEMBAGA MEDIA TWITTER. 2(1), 20–22.

Rahmadina, A. P., Setiawan, N. Y., & Rusydi, A. N. (2025). ANALISIS SENTIMEN TERHADAP KEBIJAKAN KENAIKAN PPN 12 % MENGGUNAKAN SUPPORT VECTOR MACHINE ( SVM ). 9(9), 1–10.

Rohman, S., & Agung, I. W. P. (2025). KOMPARASI ALGORITMA INDOBERT, SVM, DAN RANDOM FOREST DALAM ANALISIS SENTIMEN PROGRAM MAKAN BERGIZI GRATIS. 9(6), 9464–9471.

Salsabila, A., Priyatna, B., & Hananto, A. (2025). Komparasi Kinerja Model Naive Bayes , SVM , dan BERT dalam Klasifikasi Sentimen Ulasan Pada Aplikasi YUMMY. 4(2), 42–47.

Syafia, A. N., Hidayattullah, M. F., & Suteddy, W. (2023). Studi Komparasi Algoritma SVM Dan Random Forest Pada Analisis Sentimen Komentar Youtube BTS. 8(3), 207–212.

Tanggraeni, A. I., & Sitokdana, M. N. N. (2022). Analisis Sentimen Aplikasi E-Government Pada Google Play Menggunakan Algoritma Naïve Bayes. 9(2), 785–795.

Ulinuha, A., Majid, E., Nuari, R., Indonesia, U. T., & Lampung, B. (2025). PERFORMANCE COMPARISON OF BERT METRICS AND CLASSICAL MACHINE LEARNING MODELS ( SVM , NAIVE BAYES ) FOR SENTIMENT ANALYSIS PERBANDINGAN KINERJA METRIK BERT DAN MODEL MACHINE LEARNING KLASIK ( SVM , NAIVE BAYES ) UNTUK. 10(2), 741–752.