Title: (Almost) 200 Years of News-Based Economic Sentiment
Presenter: Jules van Binsbergen (University of Pennsylvania)
Discussant: Baozhong Yang (Georgia State University)
Host: Andy Neuhierl (Washington University in St. Louis)
Date: June 20, 2024 12-1pm Eastern Time

00:00:00​​​ Welcome remarks
00:01:55 Presentation
00:34:20 Discussion
00:55:35 Q&A

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.

ABFR:
ABFR is an interdisciplinary community of scholars with an interest in the methodology, applications, and socioeconomic implications of AI and big data for a wide range of areas in economics and finance. The forum organizes monthly presentations and discussions of papers by the leading world experts in the area, followed by an informal general post-seminar discussion. The virtual talks take place on the last Thursday
of each month from 12-1pm ET. For more information about the seminar series, including registration, please visit our website:
https://www.abfr-forum.org​​

ABFR is organized by Maryam Farboodi, Serhiy Kozak, Andy Neuhierl, Markus Pelger, and Lea Stern. It is also supported by Svetlana Bryzgalova, Lin William Cong, and The Advisory Committee, which includes Kay Giesecke, Gerald Hoberg, Wei Jiang, Bryan Kelly, Stefan Nagel, Andrew Patton, and Laura Veldkamp. ABFR hosting institutions are the Cornell FinTech Initiative and the Stanford AFTLab.