Public perception analysis on COVID-19 tweets using hybridised method

One of the most widely used social media sites, now a days, is Twitter. During COVID-19 pandemic, people used Twitter to see the daily news and tweet and retweet something on Twitter. This paper mainly focuses on sentiment analysis using tweets that have been performed during the COVID-19 pandemic. Based on Text (Tweets) and Sentiment (i.e., Positive and Negative), various computational models are used for this work, viz., long short-term memory (LSTM) and simple recurrent neural network (SimpleRNN). LSTM yields the best accuracy (92%). Based on the data, both these models provide meaningful forecasts, but in order to maintain confidence, explainable artificial intelligence (XAI) has been combined with both models. It transforms a 'black box' model into a reliable model, increasing people's impact and level of confidence in the suggested models.