Presenter: Jules van Binsbergen
Affiliation: University of Pennsylvania, Wharton School.
Paper: (Almost) 200 Years of News-Based Economic Sentiment.
Date: March 05, 2024.
Time: 13:00 GMT (15:00 Israel Time)
Abstract: Using text from 200 million pages of 13,000 US local newspapers and machine learning methods, we construct a 170-year-long measure of economic sentiment at the country and state levels, that expands existing measures in both the time series (by more than a century) and the cross-section. Our measure predicts GDP (both nationally and locally), consumption, and employment growth, even after controlling for commonly-used predictors, as well as monetary policy decisions. Our measure is distinct from the information in expert forecasts and leads its consensus value. Interestingly, news coverage has become increasingly negative across all states in the past half-century.
Coauthors: Svetlana Bryzgalova (London Business School), Mayukh Mukhopadhyay (London Business School), and Varun Sharma (Indiana University).