2020/05/11 by Baani Leen Kaur Jolly, Palash Aggrawal, Jolly, Baani Leen Kaur +9
Computer Science · Psychology · Social Sciences · #Computation and Language (cs.CL) #Computers and Society (cs.CY) #FOS: Computer and information sciences #Mental Health via Writing #Misinformation and Its Impacts #Sentiment Analysis and Opinion Mining #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.2005.05513
openalex publication_date 2020/05/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
COVID-19 infodemic has been spreading faster than the pandemic itself. The\nmisinformation riding upon the infodemic wave poses a major threat to people's\nhealth and governance systems. Since social media is the largest source of\ninformation, managing the infodemic not only requires mitigating of\nmisinformation but also an early understanding of psychological patterns\nresulting from it. During the COVID-19 crisis, Twitter alone has seen a sharp\n45% increase in the usage of its curated events page, and a 30% increase in its\ndirect messaging usage, since March 6th 2020. In this study, we analyze the\npsychometric impact and coupling of the COVID-19 infodemic with the official\nbulletins related to COVID-19 at the national and state level in India. We look\nat these two sources with a psycho-linguistic lens of emotions and quantified\nthe extent and coupling between the two. We modified path, a deep skip-gram\nbased open-sourced lexicon builder for effective capture of health-related\nemotions. We were then able to capture the time-evolution of health-related\nemotions in social media and official bulletins. An analysis of lead-lag\nrelationships between the time series of extracted emotions from official\nbulletins and social media using Granger's causality showed that state\nbulletins were leading the social media for some emotions such as Medical\nEmergency. Further insights that are potentially relevant for the policymaker\nand the communicators actively engaged in mitigating misinformation are also\ndiscussed. Our paper also introduces CoronaIndiaDataset2, the first social\nmedia based COVID-19 dataset at national and state levels from India with over\n5.6 million national and 2.6 million state-level tweets. Finally, we present\nour findings as COVibes, an interactive web application capturing psychometric\ninsights captured upon the CoronaIndiaDataset, both at a national and state\nlevel.\n