Global evidence of expressed sentiment alterations during the COVID-19 pandemic

• DOI: 10.1038/s41562-022-01312-y
• Publication Date: 2022-03-17T17:11:58Z
• Authors: Jianghao Wang; Yichun Fan; Juan Palacios; Yuchen Chai; Nicolas Guetta-Je...; Nick Obradovich; Chenghu Zhou; Siqi Zheng
• Keywords: Pandemic; 2019-20 coronavirus outbreak

The COVID-19 pandemic has created unprecedented burdens on people's physical health and subjective well-being. While countries worldwide have developed platforms to track the evolution of infections deaths, frequent global measurements affective states gauge emotional impacts related policy interventions remain scarce. Using 654 million geotagged social media posts in over 100 countries, covering 74% world population, coupled with state-of-the-art natural language processing techniques, we develop a dataset expressed sentiment indices national- subnational-level daily basis. We present two motivating applications using data from first wave (from 1 January 31 May 2020). First, regression discontinuity design, provide consistent evidence that outbreaks caused steep declines globally, followed by asymmetric, slower recoveries. Second, applying synthetic control methods, find moderate no effects lockdown policies sentiment, large heterogeneity across countries. This study shows how data, when machine learning can real-time states. tweets Wang et al. examine during pandemic. They decline worldwide, lockdowns differed