Search

Topic modelling with innovative deep learning methods has gained interest for a wide range of applications that includes COVID-19. It can provide, psychological, social and cultural insights for understanding human behaviour in extreme events such as the COVID-19 pandemic. In this paper, we use prominent deep learning-based language models for COVID-19 topic modelling taking into account data from the emergence (Alpha) to the Omicron variant in India. Our results show that the topics extracted for the subsequent waves had certain overlapping themes such as governance, vaccination, and pandemic management while novel issues aroused in political, social and economic situations during the COVID-19 pandemic. We also find a strong correlation between the major topics with news media prevalent during the respective time period. Hence, our framework has the potential to capture major issues arising during different phases of the COVID-19 pandemic which can be extended to other countries and regions. [ABSTRACT FROM AUTHOR]

The absence of reliable registration of Covid-19 deaths in India has prevented proper assessment and monitoring of the coronavirus pandemic. In addition, India's relatively young age structure tends to conceal the severity of Covid-19 mortality, which is concentrated in older age groups. In this paper, we present four different demographic samples of Indian populations for which we have information on both their demographic structures and death outcomes. We show that we can model the age distribution of Covid-19 mortality in India and use this modeling to estimate Covid-19 mortality in the country. Our findings point to a death toll of approximately 3.2–3.7 million persons by early November 2021. Once India's age structure is factored in, these figures correspond to one of the most severe cases of Covid-19 mortality in the world. India has recorded after February 2021 the second outbreak of coronavirus that has affected the entire country. The accuracy of official statistics of Covid-19 mortality has been questioned, and the real number of Covid-19 deaths is thought to be several times higher than reported. In this paper, we assembled four independent population samples to model and estimate the level of Covid-19 mortality in India. We first used a population sample with the age and sex of Covid-19 victims to develop a Gompertz model of Covid-19 mortality in India. We applied and adjusted this mortality model on two other national population samples after factoring in the demographic characteristics of these samples. We finally derive from these samples the most reasonable estimate of Covid-19 mortality level in India and confirm this result using a fourth population sample. Our findings point to a death toll of about 3.2–3.7 million persons by late May 2021. This is by far the largest number of Covid-19 deaths in the world. Once standardized for age and sex structure, India's Covid-19 mortality rate is above Brazil and the USA. Our analysis shows that existing population samples allow an alternative estimation of deaths due to Covid-19 in India. The results imply that only one out of 7–8 deaths appear to have been recorded as a Covid-19 death in India. The estimates also point to a very high Covid-19 mortality rate, which is even higher after age and sex standardization. The magnitude of the pandemic in India requires immediate attention. In the absence of effective remedies, this calls for a strong response based on a combination of non-pharmaceutical interventions and the scale-up of vaccination to make them accessible to all, with an improved surveillance system to monitor the progression of the pandemic and its spread across India's regions and social groups. [ABSTRACT FROM AUTHOR]

Social scientists and psychologists take interest in understanding how people express emotions and 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. Advancements of deep learning-based language models have been promising for sentiment analysis with data from social networks such as Twitter. Given the situation with COVID-19 pandemic, different countries had different peaks where rise and fall of new cases affected lock-downs which directly affected the economy and employment. During the rise of COVID-19 cases with stricter lock-downs, people have been expressing their sentiments in social media. This can provide a deep understanding of human psychology during catastrophic events. In this paper, we present a framework that employs deep learning-based language models via long short-term memory (LSTM) recurrent neural networks for sentiment analysis during the rise of novel COVID-19 cases in India. The framework features LSTM language model with a global vector embedding and state-of-art BERT language model. We review the sentiments expressed for selective months in 2020 which covers the major peak of novel cases in India. Our framework utilises multi-label sentiment classification where more than one sentiment can be expressed at once. Our results indicate that the majority of the tweets have been positive with high levels of optimism during the rise of the novel COVID-19 cases and the number of tweets significantly lowered towards the peak. We find that the optimistic, annoyed and joking tweets mostly dominate the monthly tweets with much lower portion of negative sentiments. The predictions generally indicate that although the majority have been optimistic, a significant group of population has been annoyed towards the way the pandemic was handled by the authorities. [ABSTRACT FROM AUTHOR]