Analisis Sentimen Masyarakat Di Media Sosial X Terhadap Kemenkes Dengan Naive Bayes dan SVM

Andrew Ryandi, Freddy
Pratiwi, Dian
Sari, Syandra

Jurnal Sains dan Teknologi
Vol. 7 No. 1 (2025): Jurnal Sains dan Teknologi

This study examines public sentiment on social media platform X regarding Indonesia's Ministry of Health during the COVID-19 pandemic, using Naïve Bayes and Support Vector Machine (SVM) algorithms. Posts mentioning the Ministry’s official account (@KemenkesRI) were preprocessed and labeled using the VADER tool. Sentiment classification was performed with TF-IDF word weighting, and both algorithms were evaluated. Results show SVM achieved slightly higher accuracy (79%) than Naïve Bayes (77%), indicating its effectiveness in handling complex language structures, though it requires more computational resources. This research underscores the utility of SVM for analyzing public sentiment on health policies..