Abstract
In this research, a framework has been developed to analyze tweets to understand the impact of the COVID-19 pandemic on various sectors in India through natural language processing and deep learning. Topic modeling technique has been used to extract various themes around the COVID-19 pandemic in India from 17 September to 17 November 2020. Majority of the tweets are related to the effect of COVID-19 pandemic on economy, education, deaths, air quality, and awareness. A sentiment analysis has been performed to understand people’s reactions during the pandemic. To perform the sentiment analysis, a bidirectional LSTM model has been developed that yields 0.94 recall for positive tweets and 0.89 precision for negative tweets and 77.52% overall accuracy. This study shows a strong correlation between lagged number of deaths and negative sentiments, which probably indicates that the number of COVID-related death negatively impacts on people’s perception towards various socio-economic and environmental aspects during COVID pandemic in India. This research has developed a novel georeferencing model that can retrieve location context from the ungeotagged tweets to analyze people’s perception towards COVID at different locations in India, which will further help in understanding situational awareness and support various policy planning and strategic decision-making measures.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
