StockTwits Classified Sentiment and Stock Returns

59 Pages Posted: 27 Aug 2020 Last revised: 23 Jun 2022

See all articles by Marc-Aurèle Divernois

Marc-Aurèle Divernois

EPFL; Swiss Finance Institute

Damir Filipović

Ecole Polytechnique Fédérale de Lausanne; Swiss Finance Institute

Date Written: September 3, 2020

Abstract

We classify StockTwits messages into bullish, bearish or neutral classes to create firm-individual sentiment polarity time-series. Polarity is positively associated with contemporaneous stock returns. On average, polarity is not able to predict next-day stock returns but when we focus on specific events (defined as sudden peak of message volume), polarity has predictive power on abnormal returns.

Keywords: Investor sentiment, Event study, Polarity, Social Media, Microblogging, Natural Language Processing

JEL Classification: G11, G14, C32

Suggested Citation

Divernois, Marc-Aurèle and Filipovic, Damir, StockTwits Classified Sentiment and Stock Returns (September 3, 2020). Swiss Finance Institute Research Paper No. 21-33, Available at SSRN: https://ssrn.com/abstract=3657034 or http://dx.doi.org/10.2139/ssrn.3657034

Marc-Aurèle Divernois (Contact Author)

EPFL ( email )

Quartier UNIL-Dorigny, Bâtiment Extranef, # 211
40, Bd du Pont-d'Arve
CH-1015 Lausanne, CH-6900
Switzerland

Swiss Finance Institute ( email )

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

Damir Filipovic

Ecole Polytechnique Fédérale de Lausanne ( email )

Odyssea
Station 5
Lausanne, 1015
Switzerland

HOME PAGE: http://people.epfl.ch/damir.filipovic

Swiss Finance Institute

c/o University of Geneva
40, Bd du Pont-d'Arve
CH-1211 Geneva 4
Switzerland

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

Paper statistics

Downloads
339
Abstract Views
1,214
rank
124,131
PlumX Metrics