Exploration of COVID 19 Tweets Data for the Prediction of Negative Ontologies through Deep Learning Techniques

COVID-19 is an infectious disease, which was first appeared in December 2019 in Wuhan, China. This virus has spread all over the world. So in a situation like this, Twitter is helping people by giving the latest information and to connect with others. As the WHO giving health information, this paper work is an implementation of automation for extracting details of Covid-19 from the latest Tweets of Twitter Social media. Most of the people started with Negative tweets about covid19, but with increasing time people shifted towards positive and neutral comments. At some time most of the comments are about winning against coronavirus. To understand the people’s opinion towards this pandemic through their tweets, we have tried to come up with an algorithm that will try to analyze the tweets using the modern computational power and some of the advanced algorithms and finally concluded at a point. Sentiment analysis using LSTM (Long Short Term Memory) which is a type of Recurrent Neural Networks, has been applied to tweets having covid19 Hash tags to see people’s reactions to the pandemic. The tweets are classified and labeled as positive, negative, and neutral then visualized the result. Tweets are categorized into three classes and derive some useful patterns from them and trying to come up with some generalized algorithms so that it cannot only be applied for Covid19 or some health-related, rather apply all kind of tweets or some other social media platform such as Instagram or LinkedIn.