Global sentiment analysis over third wave COVID19 tweets

Internet users are increasing rapidly during the last decade, and after the Covid-19 outbreak, social media platforms became the favorite source to express public responses. They are using Twitter, a free microblogging site, to express their thoughts, joys, and sorrows spontaneously. Researchers take great interest in analyzing public sentiments with the help of Data science techniques like natural language processing and machine learning methods, to predict public suggestions on topics of social concerns. In the proposed research article, we have collected public tweets during the third wave of Covid19 from 21st to 31st January 2022, and public sentiments are observed with 12 popular Machine Learning algorithms and commonly used words are represented as n-grams and here three n-grams (Unigram, Bigram, and Trigram) are collected and prediction is also observed on these data. It is observed that in all the cases LinearSVC presents the highest classification accuracy of approx. 96% for covid datasets. It has also worked well on all the three n-gram datasets with accuracies of   96.39% for unigram, 95.24 for bigram, and 87.70% for trigram. data scienc