Public Sentiment Analysis Towards Astrazeneca Vaccine in Indonesia Using Multinomial Naive Bayes

Abstrak

The COVID-19 virus, which first emerged in Wuhan in 2019, has spread globally, as one of the effect, various vaccination efforts despite ongoing debates over the long-term effectiveness of the vaccines. The Indonesian government sought to accelerate its vaccination program by securing millions of vaccine doses; however, public responses varied, with concerns primarily related to safety, effectiveness, and religious considerations. This study aims to analyze public opinion regarding the COVID-19 vaccine, specifically the AstraZeneca vaccine, by examining sentiment data from Twitter. Data were collected using the Twitter API and underwent preprocessing steps such as tokenization, stopword removal, and stemming. The processed data were then converted into numerical form using the TF-IDF method before being classified using the Multinomial Naive Bayes algorithm. The model’s performance was evaluated using metrics such as accuracy, precision, recall, and F1-score to identify positive, negative, or neutral sentiments. The results show that the Multinomial Naive Bayes model effectively classified public sentiment toward the side effects of the AstraZeneca vaccine, resulting an accuracy of 86.91%, precision of 89.26%, and recall of 85.26%. These results indicate that the model is highly effective in identifying positive sentiments with a high level of accuracy.

Identifier

• DOI: https://doi.org/10.46229/jifotech.v5i2.1007
• OpenAlex: https://openalex.org/W7134823624