In this research, we collected 70,000 COVID–19 vaccine-related geotagged Twitter posts from nine African countries. The duration is from December 2020 to February 2022. We used VADER to classify the tweets into three sentiment classes (positive, negative, and neutral). The outputs were validated using machine learning classification algorithms, including, Naive Bayes, Logistic Regression, Support Vector Machines, Decision Tree, and K-Nearest Neighbour. We identified hotspots by clustering the sentiment of these tweets using the point-based location technique. These hotspots were visualised on the map using ArcGIS Online. On the map, we used green to represent positive sentiment dominance, red to represent negative sentiment dominance, and grey to represent neutral sentiment dominance. The outcome of this research shows that social media data can be used to complement existing data in identifying hotspots during future outbreaks, especially in the areas where there is little or no available data. It can also be used to inform health policy in managing vaccine hesitancy.