Analysis of Public Sentiment Toward Gold and Bitcoin Invesments using IndoBERT
Analisis Sentimen Publik tentang Investasi Emas dan Bitcoin menggunakan IndoBERT
DOI:
https://doi.org/10.21070/ups.11204Keywords:
Bitcoin, Class Weight, Fine-tuning, IndoBERT, Sentiment AnalysisAbstract
The development of Gold and Bitcoin investments has driven increased public opinion on social media, especially on the "Ngomongin Uang" financial education channel. The massive volume of comments and informal language makes manual sentiment analysis ineffective. This study aims to map public sentiment towards Gold and Bitcoin investments and evaluate IndoBERT's capability in classifying Indonesian comments. The research data consisted of 4,909 unique comments from YouTube and TikTok grouped into positive, neutral, and negative sentiments. The method utilized was the fine-tuning of the indobenchmark/indobert-base-p2 variant using class weight and topic insertion (prepend) strategies to overcome class imbalance. The results showed that the A4 configuration (5 epochs, class weight, prepend, and AdamW optimizer) yielded the best performance with 72.51% accuracy and a Test Macro F1-Score of 0.6983. This strategy improved the model's ability to recognize negative sentiment with a 0.6087 recall and demonstrated stable performance across Bitcoin and Gold topics.
Downloads
References
I. R. Johan and S. A. Azariani, “Persepsi Risiko, Financial Self-Efficacy dan Minat Investasi Emas pada Generasi Z,” J. Ilmu Kel. dan Konsum., vol. 18, no. 1, pp. 26–37, 2025, doi: 10.24156/jikk.2025.18.1.26.
D. N. Ahsanah, “Emas sebagai Instrumen Investasi Jangka Panjang,” Shar-E J. Kaji. Ekon. Huk. Syariah, vol. 8, no. 1, pp. 177– 187, 2022.
A. Wicaksono, C. E. Violita, and E. R. Kamila, “Bitcoin sebagai Instrumen Investasi yang Menguntungkan,” Greenomika, vol. 4, no. 1, p. 44, 2022.
M. Hougan and D. Lawant, Cryptoassets: The Guide to Bitcoin, Blockchain, and Cryptocurrency for Investment Professionals. CFA Institute Research Foundation, 2021. [Online]. Available: https://www.cfainstitute.org/research/foundati on
D. Anisa, T. Anggraini, and K. Tambunan, “Analisis Cryptocurrency Sebagai Alat Alternatif Berinvestasi di Indonesia,” Own. Ris. dan J. Akunt., vol. 7, no. 3, 2023, doi: 10.33395/owner.v7i3.1698.
M. A. Rosid, D. O. Siahaan, and A. Saikhu, “Sarcasm Detection in Indonesian-English Code-Mixed Text Using Multihead Attention-Based Convolutional and BiDirectional GRU,” IEEE Access, 2024, doi: 10.1109/ACCESS.2024.3436107.
R. I. Perwira, V. A. Permadi, D. I. Purnamasari, and R. P. Agusdin, “DomainSpecific Fine-Tuning of IndoBERT for Aspect-Based Sentiment Analysis in Indonesian Travel User-Generated Content,” J. Inf. Syst. Eng. Bus. Intell., vol. 11, no. 1, pp. 30–40, 2025, doi: 10.20473/jisebi.11.1.30-40.
A. N. Alfarobby and H. Irawan, “Analisis Sentimen Kepuasan Konsumen Pengguna Transportasi Online pada Ulasan Google Playstore Menggunakan Indobert dan Topic Modeling (Studi Kasus: Gojek dan Grab),” eProceeding Manag., vol. 11, no. 1, p. 72, 2024.
S. Riyadi, L. K. Salsabila, C. Damarjati, and R. Abdul Karim, “Sentiment Analysis of YouTube Users on Blackpink Kpop Group Using IndoBERT,” INTENSIF J. Ilm. Penelit. dan Penerapan Teknol. Sist. Inf., vol. 8, no. 2, p. 233, 2024, doi: 10.29407/intensif.v8n2.22678.
S. Aras, M. Yusuf, R. Ruimassa, E. A. B. Wambrauw, and E. B. Palalangan, “Sentiment Analysis on Shopee Product Reviews Using IndoBERT,” J. Inf. Syst. Informatics, vol. 6, no. 3, p. 1616, 2024, doi: 10.51519/journalisi.v6i3.814.
W. M. Baihaqi and A. Munandar, “Sentiment Analysis of Student Comment on the College Performance Evaluation Questionnaire Using Naïve Bayes and IndoBERT,” JUITA J. Inform., vol. 11, no. 2, pp. 213– 220, 2023.
Nurhasiyah, R. Dwiyansaputra, S. I. Murpratiwi, and A. Aranta, “Analisis Sentimen Pengguna Platform Media Sosial X pada Topik Pemilihan Presiden 2024 Menggunakan Perbandingan Model Monolingual dan Multilingual BERT,” JATI J. Mhs. Tek. Inform., vol. 9, no. 1, p. 626, 2025.
A. Jazuli, Widowati, and R. Kusumaningrum, “Aspect-Based Sentiment Analysis on Student Reviews Using the Indo-Bert Base Model,” E3S Web Conf., vol. 448, 2023, doi: 10.1051/e3sconf/202344802004.
C. Apriyadi and Styawati, “Sentiment Analysis of Cyber Attacks in Bank Syariah Indonesia Using SVM and Indobert Method,” J. Tek. Inform., vol. 6, no. 2, pp. 819–838, 2025, doi: 10.52436/1.jutif.2025.6.2.2636.
O. A. Irmawan, I. Budi, A. B. Santoso, and P. K. Putra, “Improving Sentiment Analysis and Topic Extraction in Indonesian Travel App Reviews Through BERT Fine-Tuning,” J. Nas. Pendidik. Tek. Inform., vol. 13, no. 2, p. 359, 2024.
Downloads
Additional Files
Posted
Categories
License
Copyright (c) 2026 UMSIDA Preprints Server
This work is licensed under a Creative Commons Attribution 4.0 International License.
