Questioning the News About Economic Growth: Sparse Forecasting Using Thousands of News-Based Sentiment Values

International Journal of Forecasting, Vol 35, Issue 4, pp. 1370-1386, 2019

17 Pages Posted: 30 May 2017 Last revised: 6 Jun 2021

See all articles by David Ardia

David Ardia

HEC Montreal - Department of Decision Sciences

Keven Bluteau

Université de Sherbrooke - Faculty of Administration

Kris Boudt

Ghent University; Vrije Universiteit Brussel; Vrije Universiteit Amsterdam

Date Written: July 21, 2017

Abstract

Modern calculation of textual sentiment involves a myriad of choices for the actual calibration. We introduce a general sentiment engineering framework that optimizes the design for forecasting purposes. It includes the use of the elastic net for sparse data-driven selection and weighting of thousands of sentiment values. These values are obtained by pooling the textual sentiment values across publication venues, article topics, sentiment construction methods, and time. We apply the framework to investigate the added value of textual analysis-based sentiment indices for forecasting economic growth in the US. We find that, compared to the use of high-dimensional forecasting techniques based on only economic and financial indicators, the additional use of optimized news-based sentiment values yields significant accuracy gains in forecasting the nine-month and annual growth rates of the US industrial production.

Keywords: elastic-net, US industrial production, sentiment analysis, time-series aggregation, topic-sentiment

JEL Classification: C10, C32, C49, C52, E32, E37

Suggested Citation

Ardia, David and Bluteau, Keven and Boudt, Kris, Questioning the News About Economic Growth: Sparse Forecasting Using Thousands of News-Based Sentiment Values (July 21, 2017). International Journal of Forecasting, Vol 35, Issue 4, pp. 1370-1386, 2019 , Available at SSRN: https://ssrn.com/abstract=2976084 or http://dx.doi.org/10.2139/ssrn.2976084

David Ardia

HEC Montreal - Department of Decision Sciences ( email )

3000 Côte-Sainte-Catherine Road
Montreal, QC H2S1L4
Canada

Keven Bluteau (Contact Author)

Université de Sherbrooke - Faculty of Administration ( email )

Sherbrooke, Québec J1K 2R1
Canada

Kris Boudt

Ghent University ( email )

Sint-Pietersplein 5
Gent, 9000
Belgium

Vrije Universiteit Brussel ( email )

Pleinlaan 2
http://www.vub.ac.be/
Brussels, 1050
Belgium

Vrije Universiteit Amsterdam ( email )

De Boelelaan 1105
Amsterdam, ND North Holland 1081 HV
Netherlands

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
394
Abstract Views
2,177
rank
96,366
PlumX Metrics