Economic Linkages Inferred from News Stories and the Predictability of Stock Returns

53 Pages Posted: 5 Dec 2013 Last revised: 30 Dec 2015

See all articles by Anna Scherbina

Anna Scherbina

Brandeis University

Bernd Schlusche

Board of Governors of the Federal Reserve System

Date Written: December 28, 2015

Abstract

We show that news stories contain information about economic linkages between firms and document that information diffuses slowly across linked stocks. Specifically, we identify linked stocks from co-mentions in news stories and find that linked stocks cross-predict one another's returns in the future. Our results indicate that information can flow from smaller to larger stocks and across industries. Content analysis of common news stories reveals many types of firm linkages that have not been previously studied. We find that the cross-predictability in returns remains even after firm pairs with customer-supplier ties are removed. Results show that both limited attention and slow processing of complex information contribute to slow information diffusion.

Keywords: News Media, Soft Information, Linked Stocks, Information Leadership, Lead-Lag Effect, Complex Information, Limited Attention, Market Efficiency

JEL Classification: G10, G12, G14, G17

Suggested Citation

Scherbina, Anna D. and Schlusche, Bernd, Economic Linkages Inferred from News Stories and the Predictability of Stock Returns (December 28, 2015). Available at SSRN: https://ssrn.com/abstract=2363436 or http://dx.doi.org/10.2139/ssrn.2363436

Anna D. Scherbina (Contact Author)

Brandeis University ( email )

415 South Street
Waltham, MA 02453
United States

HOME PAGE: http://sites.google.com/a/brandeis.edu/anna-scherbina/

Bernd Schlusche

Board of Governors of the Federal Reserve System ( email )

20th Street and Constitution Avenue NW
Washington, DC 20551
United States

Register to save articles to
your library

Register

Paper statistics

Downloads
633
rank
40,029
Abstract Views
3,100
PlumX Metrics
!

Under construction: SSRN citations while be offline until July when we will launch a brand new and improved citations service, check here for more details.

For more information