Can Sentiment Analysis and Option Volume Anticipate Future Returns?

Computational Economics, 2017, DOI: 10.1007/ s10614-017-9694-4

Stevens Institute of Technology School of Business Research Paper No. 2015–59

26 Pages Posted: 29 May 2015 Last revised: 19 Jul 2017

Patrick Houlihan

Stevens Institute of Technology

Germán G. Creamer

Stevens Institute of Technology

Date Written: March 1, 2017

Abstract

This paper evaluates if sentiment extracted from social media and options volume anticipates future asset return. Using both textual based data and a particular market data derived call-put ratio, between July 2009 and September 2012, this research shows that: 1) features derived from market data and a call-put ratio improve model performance, and 2) sentiment derived from StockTwits, a social media platform for the financial community, further improves model performance.

Keywords: Social Media, Investor Sentiment, Behavioral Finance, Machine Learning

JEL Classification: G02, G12, C32, C15, C49, C63

Suggested Citation

Houlihan, Patrick and Creamer, Germán G., Can Sentiment Analysis and Option Volume Anticipate Future Returns? (March 1, 2017). Computational Economics, 2017, DOI: 10.1007/ s10614-017-9694-4; Stevens Institute of Technology School of Business Research Paper No. 2015–59. Available at SSRN: https://ssrn.com/abstract=2611210 or http://dx.doi.org/10.2139/ssrn.2611210

Patrick Houlihan (Contact Author)

Stevens Institute of Technology ( email )

Hoboken, NJ 07030
United States

Germán G. Creamer

Stevens Institute of Technology ( email )

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

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

Paper statistics

Downloads
228
Rank
110,568
Abstract Views
1,197