This paper quantifies global demand, supply, and uncertainty shocks and compares two major global recessions: the 2008-09 Great Recession and the COVID-19 pandemic. Two alternative approaches are used to decompose economic shocks: text mining techniques on earning call transcripts and a structural Bayesian vector autoregression model. The results highlight sharp contrast in the size of supply and demand shocks over time and across sectors. While the Great Recession was characterized by demand shocks, COVID-19 caused sizable disruptions to both demand and supply. These shocks were broad-based with varying relative importance across major sectors. Furthermore, certain sub-sectors, such as professional and business services, internet retail, and grocery/department stores, fared better than others during the pandemic. The results imply that both targeted policies and conventional countercyclical fiscal and monetary policy can accelerate the economic recovery. Large demand shocks highlight an environment of deficient demand with countercyclical policy calibrated to the size of these shocks.