Fine-tuned IndoBERT for stock market sentiment analysis: evidence from CNBC Indonesia news

Tri Agung Jiwandono (University of Technology Yogyakarta)
MS Hendriyawan Achmad (University of Technology Yogyakarta)
Suhirman Suhirman (University of Technology Yogyakarta)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 42, No 3: June 2026

Financial sentiment analysis in Indonesian markets faces significant accuracy challenges, with existing models achieving only 78-81% accuracy. We present a fine-tuned IndoBERT-Large model for classifying sentiment in Indonesian stock market news headlines, trained on 9,819 CNBC Indonesia headlines (January 2024-March 2025). Through systematic hyperparameter optimization and stratified vocabulary-balanced splitting, our model achieved 94.20% accuracy, surpassing previous baselines by 4-16 percentage points. These results demonstrate IndoBERT's effectiveness for Indonesian financial NLP and its potential for real-time market monitoring and investment decision support systems.