This paper investigates the role of sentiment in the US macro economy from 1920 to 1934. We use 2.4 million digitized articles from the Wall St Journal to algorithmically derive a monthly sentiment index. A ten variable vector error correction model is then used to identify shocks to sentiment that are orthogonal to the fundamentals of the economy. We show that the identified “pure” sentiment shocks have economically significant effects on Industrial Production, the S&P500 stock index, money supply (M2), credit spreads, terms spreads, interest rates and prices. We are further able to delineate both the timing and strength of the shocks and their subsequent effects on the economy using historical decompositions. These suggest impacts of up to 9%.
First version: May 2020. This version: February 2021
