COVID-19 sentiment analysis via deep learning during the rise of novel cases

Social scientists and psychologists take interest in understanding how people express emotions or sentiments when dealing with catastrophic events such as natural disasters, political unrest, and terrorism. The COVID-19 pandemic is a catastrophic event that has raised a number of psychological issues such as depression given abrupt social changes and lack of employment. During the rise of COVID-19 cases with stricter lock downs, people have been expressing their sentiments in social media which can provide a deep understanding of how people physiologically react to catastrophic events. In this paper, we use deep learning based language models via long short-term memory (LSTM) recurrent neural networks for sentiment analysis on Twitter with a focus of rise of novel cases in India. We use the LSTM model with a global vector (GloVe) for word representation in building a language model. We review the sentiments expressed for selective months covering the major peak of new cases in 2020. We present a framework that focuses on multi-label sentiment classification using LSTM model and GloVe embedding, where more than one sentiment can be expressed at once. Our results show that the majority of the tweets have been positive with high levels of optimism during the rise of the COVID-19 cases in India. We find that the number of tweets significantly lowered towards the peak of new cases. We find that the optimistic and joking tweets mostly dominated the monthly tweets and there was a much lower number of negative sentiments expressed. This could imply that the majority were generally positive and some annoyed towards the way the pandemic was handled by the authorities as their peak was reached.