Do Newspaper Articles Predict Aggregate Stock Returns?

University of St.Gallen, School of Finance Research Paper No. 2012/4

Journal of Behavioral Finance, 15(3), 2014, pp. 195-213.

40 Pages Posted: 16 Nov 2011 Last revised: 25 Jan 2016

See all articles by Manuel Ammann

Manuel Ammann

University of St. Gallen - School of Finance

Roman Frey

University of St. Gallen - Swiss Institute of Banking and Finance

Michael Verhofen

University of St. Gallen - Swiss Institute of Banking and Finance

Date Written: November 15, 2011

Abstract

We analyze whether newspaper content can predict aggregate future stock returns. Our study is based on articles published in the Handelsblatt, a leading German financial newspaper, from July 1989 to March 2011. We summarize newspaper content in a systematic way by constructing word-count indices for a large number of words. Word-count indices are instantly available and therefore potentially valuable financial indicators. Our main finding is that the predictive power of newspaper content has increased over time, particularly since 2000. We find that a cluster analysis approach increases the predictive power of newspaper articles substantially. To obtain optimal predictive power, we need at least seven clusters. Our analysis shows that newspaper content is a valuable predictor of future DAX returns in and out of sample.

Keywords: Wordcount, Text Mining, Market Efficiency, Tactical Asset Allocation

JEL Classification: G10

Suggested Citation

Ammann, Manuel and Frey, Roman and Verhofen, Michael, Do Newspaper Articles Predict Aggregate Stock Returns? (November 15, 2011). University of St.Gallen, School of Finance Research Paper No. 2012/4, Journal of Behavioral Finance, 15(3), 2014, pp. 195-213., Available at SSRN: https://ssrn.com/abstract=1959916 or http://dx.doi.org/10.2139/ssrn.1959916

Manuel Ammann

University of St. Gallen - School of Finance ( email )

Unterer Graben 21
St.Gallen, CH-9000
Switzerland

Roman Frey

University of St. Gallen - Swiss Institute of Banking and Finance ( email )

Rosenbergstrasse 52
St. Gallen, CH-9000
Switzerland

Michael Verhofen (Contact Author)

University of St. Gallen - Swiss Institute of Banking and Finance ( email )

CH-9000
Switzerland

Do you have negative results from your research you’d like to share?

Paper statistics

Downloads
625
Abstract Views
4,193
Rank
78,301
PlumX Metrics