Key points are not available for this paper at this time.
How different cultures react and respond given a crisis is predominant in a's norms and political will to combat the situation. Often the decisions are necessitated by events, social pressure, or the need of the hour, may not represent the will of the nation. While some are pleased with it, might show resentment. Coronavirus (COVID-19) brought a mix of similar from the nations towards the decisions taken by their respective. Social media was bombarded with posts containing both positive and sentiments on the COVID-19, pandemic, lockdown, hashtags past couple months. Despite geographically close, many neighboring countries reacted to one another. For instance, Denmark and Sweden, which share many, stood poles apart on the decision taken by their respective. Yet, their nation's support was mostly unanimous, unlike the South neighboring countries where people showed a lot of anxiety and. This study tends to detect and analyze sentiment polarity and demonstrated during the initial phase of the pandemic and the lockdown employing natural language processing (NLP) and deep learning techniques Twitter posts. Deep long short-term memory (LSTM) models used for estimating sentiment polarity and emotions from extracted tweets have been trained to state-of-the-art accuracy on the sentiment140 dataset. The use of showed a unique and novel way of validating the supervised deep models on tweets extracted from Twitter.
Imran et al. (Sun,) studied this question.