Sentiment analysis can be applied in several fields, particularly in healthcare. This study aims to use it to analyze patients’ sentiments regarding COVID-19 vaccination. Since vaccination is considered an essential preventive measure, it plays a major role in disease prevention. However, a portion of the population remains hesitant to get vaccinated. The objective of this study is to analyze positive, negative, and neutral sentiments by examining their geographic distribution, temporal evolution, and identifying the underlying reasons behind each sentiment. This will help target areas where vaccine hesitancy is more pronounced. Then, sentiment analysis models such as SVM (Support Vector Machine), KNN (K-Nearest Neighbors), and BERT (Bidirectional Encoder Representations from Transformers) will be applied, with the latter having proven its efficiency as a powerful tool capable of classifying sentiments expressed in text while capturing their context. The expected outcomes of this study include identifying countries with higher vaccine hesitancy and those where vaccination is more accepted, along with the reasons behind these attitudes. This work will be useful for health authorities, as it will enable them to better target populations hesitant about COVID-19 vaccination and implement interventions to reduce hesitancy rates in these regions.