Hybrid Relevance and Sentiment Classification of Indonesian Gold Tweets Using Machine Learning for Market Risk Signal Extraction

Antika Zahrotul Kamalia; Indra  Indra; Arief  Wibowo; Jan Everhard  Riwurohi; Shiza  Hassan

doi:10.59395/ijadis.v7i1.1517

Authors

Antika Zahrotul Kamalia Department of Informatics Engineering, Universitas Pelita Bangsa, Indonesia
Indra Indra Department of Computer Science, Universitas Budi Luhur, Indonesia
Arief Wibowo Department of Computer Science, Universitas Budi Luhur, Indonesia
Jan Everhard Riwurohi Department of Computer Science, Universitas Budi Luhur, Indonesia
Shiza Hassan Department of Computer Science, UIT University, Pakistan

DOI:

https://doi.org/10.59395/ijadis.v7i1.1517

Keywords:

Gold, Classification, Sentiment, Machine Learning, Risk

Abstract

This study proposes a hybrid relevance–sentiment classification framework to analyze public opinion on physical Antam gold from Indonesian Twitter data and to support exploratory market-risk signal extraction. Tweets were collected during February–November 2025, after preprocessing and text-normalized deduplication, 1,271 unique tweets were retained. The approach combines weak supervision (rule-/lexicon-based silver labels) with TF-IDF-based machine learning in two stages: (1) relevance classification to separate tweets genuinely discussing physical Antam gold from non-relevant contexts (e.g., ANTM stock/capital-market discussions), and (2) two-class sentiment classification (positive vs negative) applied to relevance-filtered tweets. Random Forest achieved the strongest relevance performance (Accuracy = 0.984; macro-F1 = 0.943; 5-fold CV macro-F1 = 0.928 ± 0.033). For sentiment classification, performance was moderate and close across models; the most stable model under cross-validation (Logistic Regression/Naive Bayes) was used for downstream aggregation. Sentiment outputs were aggregated into a monthly sentiment index for descriptive comparison with gold prices; the observed association was weak, indicating that the index is better interpreted as a risk-perception proxy rather than a direct price predictor.

1160 1649

Downloads

Download data is not yet available.

References

[1] D. Korsah, Lord Mensah, K. A. Osei, and G. Amewu, “Dynamic connectedness, hedge and safe-haven effects: cryptocurrencies, precious metals and African stock markets,” Int. J. Emerg. Mark., 2025, doi: 10.1108/IJOEM-06-2024-1090. DOI: https://doi.org/10.1108/IJOEM-06-2024-1090

[2] M. Zaenal Asikin, “Peran Emas sebagai Lindung Nilai terhadap Ketidakpastian Pasar Keuangan Global,” Hawalah Kaji. Ilmu Ekon. Syariah, vol. 3, no. 3, pp. 123–133, 2024, doi: 10.57096/hawalah.v3i3.54. DOI: https://doi.org/10.57096/hawalah.v3i3.54

[3] U. Yeniley, “The Role of Gold ETFs in Market Stability, Price Discovery, and Economic Dynamics during Crises,” Asian J. Econ. Bus. Account., vol. 25, no. 1, pp. 60–74, 2025, doi: 10.9734/ajeba/2025/v25i11633. DOI: https://doi.org/10.9734/ajeba/2025/v25i11633

[4] M. H. Rustam, D. Handoko, A. Rustam, and M. April, “the Dynamics of Court Decisions in the Civil Dispute Over Gold Sales Between Pt Antam Tbk and Budi Said and Its Implications for the Application of Civil Law in bertnesia,” vol. 23, no. 158, pp. 165–176, 2025.

[5] F. Febriansyah and M. A. Adlan, “Saham Sebagai Instrumen Investasi: Peluang, Risiko, dan Strategi Investasi Di Tengah Dinamika Ekonomi Global 2024 – 2025,” vol. 3, no. 2, pp. 207–220, 2025. DOI: https://doi.org/10.61994/econis.v3i2.1135

[6] Muhammad Hisam, “Menavigasi Volatilitas Pasar: Wawasan Tentang Instrumen Keuangan Dan Strategi Investasi,” Curr. J. Ekon. dan Perbank. Syariah Vol., vol. 02, no. April, pp. 315–328, 2024. DOI: https://doi.org/10.32806/ccy.v2i2.248

[7] S. I. Blihaq and R. A. Muthmainah, “Value-at-Risk ( VaR ) Modeling of LQ45 Stocks Using the GARCH Approach,” vol. 6, no. 6, pp. 509–518, 2025. DOI: https://doi.org/10.46336/ijqrm.v6i4.1112

[8] I. Akgül, M. Bildirici, and S. Özdemir, “Evaluating the Nonlinear Linkage between Gold Prices and Stock Market Index Using Markov-Switching Bayesian VAR Models,” Procedia - Soc. Behav. Sci., vol. 210, pp. 408–415, 2015, doi: 10.1016/j.sbspro.2015.11.388. DOI: https://doi.org/10.1016/j.sbspro.2015.11.388

[9] Nida Shaffitry Hafidz, “Factors Influencing Stock Valuation: A Systematic Review of the Role of Market Fundamentals and Sentiment Nida,” vol. I, pp. 13–20, 2024.

[10] F. Aminarty, N. Amina, A. Indrijawati, and M. I. Ferdiansah, “Interaksi Antara Perilaku Investor dan Tren Pasar Modal,” Adv. Manag. Financ. Report., vol. 3, no. 3, pp. 335–362, 2025, doi: 10.60079/amfr.v3i3.531. DOI: https://doi.org/10.60079/amfr.v3i3.531

[11] A. Wibowo, AI & ML Di Bidang Keuangan: Mengatasi Masalah Kompleks dan Aplikasi Lingkungan, Sosial dan Tatakelola(ESG). Semarang: Prima Agust Teknik.

[12] Christophorus Bintang Saputra and D. P. Koesrindartoto, “Pemanfaatan Analisis Sentimen Youtube untuk Prediksi Harga Saham: Studi pada Investor Retail Indonesia,” J. Manaj., vol. 21, no. 1, pp. 1–17, 2024, doi: 10.25170/jm.v21i1.5184. DOI: https://doi.org/10.25170/jm.v21i1.5184

[13] M. Li, S. Guo, and R. Liu, “BERT-based Consumer Sentiment Analysis for Personalized Marketing Strategies,” Inform., vol. 49, no. 28, pp. 211–226, 2025, doi: 10.31449/inf.v49i28.8232. DOI: https://doi.org/10.31449/inf.v49i28.8232

[14] F. Kurniawan, H. Agustian, D. Dermawan, R. Nurdin, N. Ahmadi, and O. Dinaryanto, “Hybrid Rule-Based and Reinforcement Learning for Urban Signal Control in Developing Cities: A Systematic Literature Review and Practice Recommendations for Indonesia,” Appl. Sci., vol. 15, no. 19, p. 10761, 2025, [Online]. Available: https://doi.orgorg/10.3390/app151910761 DOI: https://doi.org/10.3390/app151910761

[15] M. M. Yousuf and S. A. Sofi, “Bug Classification in quantum software: a rule-based framework and its evaluation,” Autom. Softw. Eng., vol. 33, no. 1, pp. 1–25, 2026, doi: 10.1007/s10515-025-00585-7. DOI: https://doi.org/10.1007/s10515-025-00585-7

[16] N. Rahayu, S. Indri Yani, M. Marwah, and A. Pratama, “Analisis Sentimen terhadap Terorisme pada Platform Twitter menggunakan Support Vector Machine,” J. Manaj. Inform. Sist. Inf. dan Teknol. Komput., vol. 4, no. 1, pp. 430–441, 2025, doi: 10.70247/jumistik.v4i1.152. DOI: https://doi.org/10.70247/jumistik.v4i1.152

[17] B. K. Shrivash, D. K. Verma, and P. Pandey, “A Novel Framework for Text Preprocessing using NLP Approaches and Classification using Random Forest Grid Search Technique for Sentiment Analysis,” Econ. Comput. Econ. Cybern. Stud. Res., vol. 59, no. 2, pp. 91–107, 2025, doi: 10.24818/18423264/59.2.25.06. DOI: https://doi.org/10.24818/18423264/59.2.25.06

[18] W. Y. Melhem, A. Abdi, and F. Meziane, “Deep Learning Classification of Traffic-Related Tweets: An Advanced Framework Using Deep Learning for Contextual Understanding and Traffic-Related Short Text Classification,” Appl. Sci., vol. 14, no. 23, 2024, doi: 10.3390/app142311009. DOI: https://doi.org/10.3390/app142311009

[19] Z. Shahbazi, R. Jalali, and Z. Shahbazi, “AI-Driven Sentiment Analysis for Discovering Climate Change Impacts,” Smart Cities, vol. 8, no. 4, pp. 1–20, 2025, doi: 10.3390/smartcities8040109. DOI: https://doi.org/10.3390/smartcities8040109

[20] A. Alotaibi, F. Nadeem, and M. Hamdy, “Weakly Supervised Deep Learning for Arabic Tweet Sentiment Analysis on Education Reforms: Leveraging Pre-Trained Models and LLMs with Snorkel,” IEEE Access, vol. 13, no. February, pp. 30523–30542, 2025, doi: 10.1109/ACCESS.2025.3541154. DOI: https://doi.org/10.1109/ACCESS.2025.3541154

[21] M. Alizadeh and A. Seilsepour, “A novel self-supervised sentiment classification approach using semantic labeling based on contextual embeddings,” Multimed. Tools Appl., vol. 84, no. 12, pp. 10195–10220, 2025, doi: 10.1007/s11042-024-19086-y. DOI: https://doi.org/10.1007/s11042-024-19086-y

[22] A. M. K. Mohammed, G. G. M. N. Ali, and S. S. Khairunnesa, “GSAF: An ML-Based Sentiment Analytics Framework for Understanding Contemporary Public Sentiment and Trends on Key Societal Issues,” Inf., vol. 16, no. 4, 2025, doi: 10.3390/info16040271. DOI: https://doi.org/10.3390/info16040271

[23] C. P. T. Mendoza, “Analyzing Historical Trends and Predicting Market Sentiment in Digital Currency Using Time Series Decomposition and ARIMA Models on Crypto Fear and Greed Index Data,” J. Digit. Mark. Digit. Curr., vol. 2, no. 3, pp. 270–297, 2025, doi: 10.47738/jdmdc.v2i3.37. DOI: https://doi.org/10.47738/jdmdc.v2i3.37

[24] M. Halousková and Š. Lyócsa, “Forecasting U.S. equity market volatility with attention and sentiment to the economy,” pp. 1–51, 2025, [Online]. Available: http://arxiv.org/abs/2503.19767

[25] Z. Zhang et al., “Interpretable machine learning model to predict 90-day radiographically confirmed pneumonia after chemotherapy initiation in non-Hodgkin lymphoma: development and internal validation of a single-center cohort,” Front. Med., vol. 12, no. September, pp. 1–19, 2025, doi: 10.3389/fmed.2025.1674896. DOI: https://doi.org/10.3389/fmed.2025.1674896

[26] P. R. Alapati et al., “Improving English Writing Skills Through NLP-Driven Error Detection and Correction Systems,” Int. J. Adv. Comput. Sci. Appl., vol. 16, no. 2, pp. 1098–1110, 2025, doi: 10.14569/IJACSA.2025.01602109. DOI: https://doi.org/10.14569/IJACSA.2025.01602109

[27] R. Mühlhoff and T. Willem, “Social media advertising for clinical studies: Ethical and data protection implications of online targeting,” Big Data Soc., vol. 10, no. 1, 2023, doi: 10.1177/20539517231156127. DOI: https://doi.org/10.1177/20539517231156127

[28] M. Levine, R. Philpot, S. J. Nightingale, and A. Kordoni, “Visual Digital Data, Ethical Challenges, and Psychological Science,” Am. Psychol., vol. 79, no. 1, pp. 109–122, 2024, doi: 10.1037/amp0001192. DOI: https://doi.org/10.1037/amp0001192

[29] B. R. Babu, S. Ramakrishna, and S. K. Duvvuri, “Advanced Sentiment and Trend Analysis of Twitter Data Using CNN-LSTM and Word2Vec,” 4th Int. Conf. Sentim. Anal. Deep Learn. ICSADL 2025 - Proc., pp. 1536–1543, 2025, doi: 10.1109/ICSADL65848.2025.10933031. DOI: https://doi.org/10.1109/ICSADL65848.2025.10933031

[30] K. Wang, “Multifactor prediction model for stock market analysis based on deep learning techniques,” Sci. Rep., vol. 15, no. 1, pp. 1–20, 2025, doi: 10.1038/s41598-025-88734-6. DOI: https://doi.org/10.1038/s41598-025-88734-6

[31] I. Moustati and N. Gherabi, “Bridging Behavioral Insights and Automated Trading: An Internet of Behaviors Approach for Enhanced Financial Decision-Making,” Inf., vol. 16, no. 5, 2025, doi: 10.3390/info16050338. DOI: https://doi.org/10.3390/info16050338

[32] K. Balog, Entity-Oriented Search, vol. 39. Stavanger: Springer, 2018. [Online]. Available: https://eos-book.org DOI: https://doi.org/10.1007/978-3-319-93935-3

[33] Y. Liscano, L. A. Anillo Arrieta, J. F. Montenegro, D. Prieto-Alvarado, and J. Ordoñez, “Early Warning of Infectious Disease Outbreaks Using Social Media and Digital Data: A Scoping Review,” Int. J. Environ. Res. Public Health, vol. 22, no. 7, pp. 1–34, 2025, doi: 10.3390/ijerph22071104. DOI: https://doi.org/10.3390/ijerph22071104

[34] F. Islamiah and I. Muthahharah, “Pendekatan Analisis Sentimen Terhadap Persepsi Pengguna Fintech Syariah Ammana Berbasis Algoritma Machine Learning,” vol. 4, no. 2, pp. 359–369, 2025.

[35] H. Kim-Hahm, A. S. Abou-Zaid, and A. Mohd, “News vs. Social Media: Sentiment Impact on Stock Performance of Big Tech Companies,” J. Risk Financ. Manag., vol. 18, no. 12, p. 660, 2025, doi: 10.3390/jrfm18120660. DOI: https://doi.org/10.3390/jrfm18120660

[36] A. Odunaike, “Integrating Real-Time Financial Data Streams to Enhance Dynamic Risk Modeling and Portfolio Decision Accuracy,” Int. J. Comput. Appl. Technol. Res., vol. 14, no. 08, pp. 1–16, 2025, doi: 10.7753/ijcatr1408.1001. DOI: https://doi.org/10.7753/IJCATR1408.1001

[37] P. K. Bhowmik et al., “AI-Driven Sentiment Analysis for Bitcoin Market Trends: A Predictive Approach to Crypto Volatility,” J. Ecohumanism, vol. 4, no. 4, pp. 266–288, 2025, doi: 10.62754/joe.v4i4.6729. DOI: https://doi.org/10.62754/joe.v4i4.6729

[38] D. Léber and B. Egyed, “The Sentiment Augmented GARCH-LSTM Hybrid Model for Value-at-Risk Forecasting,” Comput. Econ., 2025, doi: 10.1007/s10614-025-11042-8. DOI: https://doi.org/10.1007/s10614-025-11042-8

[39] K. V. Thomas and K. Santhosh Kumar, “Investor Sentiment and Stock Market Volatility: A Behavioral Finance Perspective,” GS WOW Wisdom Worthy Res. J., vol. 4, no. 1, pp. 37–50, 2025, doi: 10.62078/grks.2025.v04i01.005. DOI: https://doi.org/10.62078/grks.2025.v04i01.005