The news of COVID-19 that has been circulating on social media has caused melancholy, anxiety, and terror. One of these social networks is Twitter, that can be considered as a microblogging social networking that allows users to communicate via tweets up to 140 characters. Relevant hashtags, Uniform Resource Locators (URL)s, images, emojis, animated gifs, and videos can all be included in the tweets. By analyzing Covid19 hashtags on Twitter, it is possible to detect the public’s feelings and opinions about this crisis. Understanding the thoughts concealed behind a word or a phrase can help better comprehend the feelings shared on social media. and can be accomplished through Sentiment Analysis (SA). This study aims to investigate the usefulness of hashtag Covid19 tweets in identifying the emotional polarity of the COVID-19 pandemic on Twitter via a SA process. This research’s methodology produced a revolutionary Ensemble classifier, in which a boosting approach called Random Forest (RF) is combined with Bidirectional Encoder Representations from Transformers (BERT) in the same model called Ens-RF-BERT. The sentiment ratings are classified as good, negative, or neutral using an ensemble voting model based on (RF) and the (BERT). A dataset that contains tweets with the hashtag Covid19 was utilized in this study for the categorization, pre-processing, and exploratory data analysis of the tweets. The experimental assessment verifies that, when compared to individual Machine or Deep Learning classifiers used in the literature, the suggested Ensemble Voting Machine and Deep Learning approach (Ens-RF-BERT) classifier outperformed all Machine Learning approaches with 94 percent of the findings. Ens-RF-BERT performs better on the same dataset with an accuracy of 93.01 percent, precision of 94.03 percent, and recall of 93.05 percent.