Risk Premium of Social Media Sentiment

Journal of Investing 26 (3): 21-28. 2017

22 Pages Posted: 14 Feb 2019

See all articles by Patrick Houlihan

Patrick Houlihan

Stevens Institute of Technology

Germán G. Creamer

Stevens Institute of Technology, School of Business; Columbia University - Department of Computer Science

Date Written: 2017

Abstract

This research investigates the predictive capability of sentiment extrapolated from three dictionaries; financial, social media and mood states. Our findings show 1) through the Fama-Macbeth regression method, social media based sentiment measures can be used as risk factors in an asset pricing framework; 2) these sentiment measures have predictive capability when used as features in a machine learning framework, and 3) adjusting returns for market effects result in positive alpha.

Keywords: sentiment analysis, risk management, forecasting

JEL Classification: C01, C32, G02, G12

Suggested Citation

Houlihan, Patrick and Creamer, Germán G., Risk Premium of Social Media Sentiment (2017). Journal of Investing 26 (3): 21-28. 2017, Available at SSRN: https://ssrn.com/abstract=3323213 or http://dx.doi.org/10.2139/ssrn.3323213

Patrick Houlihan

Stevens Institute of Technology ( email )

Hoboken, NJ 07030
United States

Germán G. Creamer (Contact Author)

Stevens Institute of Technology, School of Business ( email )

1 Castle Point on Hudson
Hoboken, NJ 07030
United States
2012168986 (Phone)

HOME PAGE: http://www.creamer-co.com

Columbia University - Department of Computer Science ( email )

New York, NY 10027
United States

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

Paper statistics

Downloads
176
Abstract Views
1,128
Rank
289,919
PlumX Metrics