Understanding Peoples' Sentiment During Different Phases of COVID-19 Lockdown in India

Abstract

During a global pandemic like COVID-19, the success of governmental policies depends on the people's sentiments and extended cooperation towards these policies. Therefore, this study explores the prevalent discourse in social media about different aspects of the COVID-19 pandemic and the policies to manage and control it. Data from Twitter collected between 25 March 2020 and 1 July 2020 was used for topic modelling and sentiment analysis. Natural language processing-based text mining techniques were used for analysis. This study first identified different frequent COVID-19-related topics and then analyzed how the sentiments towards these topics differ across different phases of lockdown. Further, insights into how different topics were perceived by gender and age group are also discussed in this study. Finally, this study also analyzed how daily casualty due to COVID-19 influenced the public sentiments and number of daily tweets. The study provides a robust NLP-based text mining framework to predict the people's sentiment during COVID-19 lockdown in India. The insights presented in this study can help the authorities mitigate the COVID-19 pandemic effectively and help different agencies in the face of similar pandemics in the future.