Answers are grounded in this paper and cite their sources.
Fluctuations in the rupiah against the United States dollar often trigger various public responses reflected through social media, particularly Platform X. This study aims to analyze public sentiment regarding USD/IDR exchange rate fluctuations and perceptions of Indonesia's economic stability using a text mining approach. The dataset consists of 1,500 Indonesian-language tweets collected from three search topics, namely rupiah_melemah, rupiah_menguat, and ekonomi_indonesia. Data preprocessing was conducted through cleaning, case folding, tokenizing, stopword removal, and stemming. Sentiment labeling was performed using a lexicon-based approach before feature extraction using Term Frequency-Inverse Document Frequency (TF-IDF) and classification using the Naïve Bayes algorithm. The results indicate that neutral sentiment dominates public discussions with 983 tweets (65.5%), followed by positive sentiment with 378 tweets (25.2%) and negative sentiment with 139 tweets (9.3%). The findings show that the Naïve Bayes algorithm can effectively classify Indonesian-language text sentiment and provide an overview of public perceptions regarding Indonesia's economic conditions.
No takes yet. Share an insight, caveat, or question.
Sabila et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: