Perbandingan IndoBERT dan SVM dalam Analisis Sentimen Komentar YouTube pada Isu Pelemahan Nilai Tukar Rupiah

Khoirun Nisa, Anggit Wirasto, Yayak Kartika Sari

Abstract


Pelemahan nilai tukar Rupiah terhadap Dolar Amerika Serikat memicu respons masif publik Indonesia di platform media sosial, termasuk kolom komentar YouTube. Analisis sentimen terhadap komentar berbahasa Indonesia menghadapi tantangan bahasa informal, singkatan, sarkasme, dan campur kode yang tidak dapat ditangani secara optimal oleh metode konvensional. Penelitian ini membandingkan performa fine-tuning IndoBERT dengan baseline Support Vector Machine berbasis TF-IDF untuk klasifikasi sentimen tiga kelas pada komentar YouTube terkait isu nilai tukar Rupiah. Data dikumpulkan menggunakan YouTube Data API v3 dengan empat kata kunci, menghasilkan 5.581 komentar yang diproses menjadi 4.352 data setelah preprocessing dan pelabelan semi-otomatis menggunakan InSet Lexicon. Validasi label dilakukan oleh dua anotator independen dengan nilai Cohen Kappa sebesar 0,77 yang termasuk kategori Baik. Fine-tuning IndoBERT dilakukan dengan learning rate 2e-5, batch size 16, dan 5 epoch menggunakan optimizer AdamW dengan pembobotan kelas. IndoBERT mencapai akurasi 72,33 persen dengan weighted F1-Score 0,72, melampaui SVM yang memperoleh akurasi 71,87 persen dengan weighted F1-Score 0,64. Perbedaan paling signifikan tampak pada kelas minoritas, yaitu F1-Score netral IndoBERT sebesar 0,43 berbanding 0,08 sebesar SVM. Dominasi sentimen negatif sebesar 69,6 persen mengindikasikan tingginya kepanikan publik terhadap kondisi nilai tukar Rupiah.

References


N. Ma, G. Yu, X. Jin, and X. Zhu, “Quantified multidimensional public sentiment characteristics on social media for public opinion management : Evidence from the COVID- pandemic,” Front. public Heal., vol. 11, no. 2, 2023, doi: https://doi.org/10.3389/fpubh.2023.1097796.

J. Cui, Z. Wang, S. Ho, and E. Cambria, Survey on sentiment analysis : evolution of research methods and topics, vol. 56, no. 8. Springer Netherlands, 2023. doi: 10.1007/s10462-022-10386-z.

R. Obiedat, R. Qaddoura, A. L. A. M. Al-zoubi, and L. Al-qaisi, “Sentiment Analysis of Customers ’ Reviews Using a Hybrid Evolutionary SVM-Based Approach in an Imbalanced Data Distribution,” IEEE Access, vol. 10, pp. 22260–22273, 2022, doi: 10.1109/ACCESS.2022.3149482.

K. Nandini and M. Rahardi, “Sentiment Analysis of Economic Policy Comments on YouTube Using Ensemble Machine Learning,” J. Appl. Informatics Comput., vol. 9, no. 5, pp. 2607–2615, 2025.

U. Khairani et al., “Pengaruh Tahapan Preprocessing Terhadap Model IndoBERT dan IndoTWEET untuk Mendeteksi Emosi pada Komentar Akun Berita Instagram,” J. Teknol. Inf. dan Ilmu Komput., vol. 11, no. 4, 2024, doi: 10.25126/jtiik.1148315.

A. Vaswani et al., “Attention Is All You Need,” in 31st Conference on Neural Information Processing Systems, 2017.

M. C. Kenton, L. Kristina, and J. Devlin, “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” Proc. 2019 Conf. North Am. Chapter Assoc. Comput. Linguist. Hum. Lang. Technol., vol. 1, pp. 4171–4186, 2019, doi: https://doi.org/10.18653/v1/N19-1423.

B. Wilie et al., “IndoNLU : Benchmark and Resources for Evaluating Indonesian Natural Language Understanding,” Proc. 1st Conf. Asia-Pacific Chapter Assoc. Comput. Linguist. 10th Int. Jt. Conf. Nat. Lang. Process., pp. 843–857, 2020, doi: https://doi.org/10.18653/v1/2020.aacl-main.85.

C. Sun, X. Qiu, Y. Xu, and X. Huang, “How to Fine-Tune BERT for Text Classification?,” no. 2, 2020.

R. Qasim, W. H. Bangyal, M. A. Alqarni, and A. A. Almazroi, “A Fine-Tuned BERT-Based Transfer Learning Approach for Text Classification,” J. Healthc. Eng., pp. 1–17, 2022, doi: 10.1155/2022/3498123.

I. Loshchilov and F. Hutter, “Decoupled Weight Delay Regularization,” in ICLR, 2019.

L. Geni, E. Yulianti, and D. I. Sensuse, “Sentiment Analysis of Tweets Before the 2024 Elections in Indonesia Using IndoBERT Language Models,” J. Ilm. Tek. Elektro Komput. dan Inform., vol. 9, no. 3, pp. 746–757, 2024, doi: 10.26555/jiteki.v9i3.26490.

P. Sayarizki and H. Nurrahmi, “Implementation of IndoBERT for Sentiment Analysis of Indonesian Presidential Candidates,” Indones. J. Comput., vol. 9, pp. 61–72, 2024, doi: 10.34818/indojc.2024.9.2.934.

N. Putu, D. Agustina, I. D. Ayu, P. Pratiwi, I. G. Ngurah, and L. Wijayakusuma, “Public Sentiment Analysis on Demonstration Actions Using IndoBERT Based on Transfer Learning,” J. Appl. Informatics Comput., vol. 9, no. 6, 2026.

D. R. Alfinsyah and B. P. Hartato, “Evaluating the Impact of Random Over Sampling on IndoBERT Performance for Indonesian Sentiment Analysis,” J. Appl. Informatics Comput., vol. 9, no. 6, pp. 3270–3282, 2025.

F. Koto and G. Y. Rahmaningtyas, “InSet Lexicon: Evaluation of a Word List for Indonesian Sentiment Analysis in Microblogs,” IEEE Access, pp. 391–394, 2017.

A. D. Latief, A. Jarin, M. T. Uliniansyah, E. Nurfadhilah, D. Isnaeni, and N. Afra, “A Proven Sentiment Annotation Guideline for Indonesian Twitter Data,” 2023 Int. Conf. Comput. Control. Informatics its Appl., pp. 31–36, 2023, doi: 10.1109/IC3INA60834.2023.10285807.

O. D. Palupi, Y. K. Sari, and J. Iskandar, “Comparison of CNN and SVM Algorithms in Sentiment Analysis of Roblox Game Based on Bug, Loading Asset, and Connection Stability Aspects Oktaviana,” G-Tech J. Teknol. Terap., vol. 10, no. 2, pp. 710–719, 2026.


Refbacks

  • There are currently no refbacks.