<![CDATA[This research examines public sentiment toward Indonesia's industrial downstreaming policy using data sourced from X. The study employs the Naive Bayes algorithm to categorize public opinions into three sentiment types: positive, negative, and neutral. Data collection was conducted via a crawling process utilizing the X API and tools like Tweepy, followed by preprocessing steps such as data cleansing, tokenization, case normalization, stopword removal, and either stemming or lemmatization. Subsequently, the data was manually annotated using a lexicon-based sentiment method to ensure accurate classification. The findings reveal that the Naive Bayes algorithm achieved an accuracy rate of 81.75% in sentiment classification, with the highest performance observed in identifying positive sentiments. This research offers valuable insights into public perspectives on the industrial downstreaming policy and suggests recommendations for policymakers to develop strategies that better resonate with public sentiment. Leveraging X as a data source allows for real-time analysis that adapts to shifts in public opinion.]]>
Copyrights © 2025
