FINE-GRAINED SENTIMENT ANALYSIS ON BIG DATA FROM MULTI-PLATFORM IN INDONESIA

Abstract

Sentiment analysis on multi-platform big data in Indonesia presents a complex challenge, particularly in optimizing sentiment classification with higher granularity. This study develops and optimizes a Fine-Grained Sentiment Analysis model based on Indonesian Bidirectional Encoder Representations from Transformers (IndoBERT) to analyze public opinion on ChatGPT. The method is applied to big data collected from various social media platforms to improve accuracy and precision in identifying a broader spectrum of sentiments, including highly positive, positive, neutral, negative, and highly negative categories. A comparative analysis is conducted on different base models, including BERT, RoBERTa, and IndoBERT, to determine the most effective approach. Experimental results show that the optimized IndoBERT model achieves 96% accuracy and outperforms other models in terms of precision and F1-score across all sentiment categories. The study also evaluates computational efficiency and adaptability to diverse data, demonstrating that the proposed model can serve as an effective solution for gaining deeper insights into public opinion across digital platforms in Indonesia.