Sentiment stocks
Hang Dong and
Javier Gil-Bazo
International Review of Financial Analysis, 2020, vol. 72, issue C
Abstract:
To study how investor sentiment at the firm level affects stock returns, we match more than 58 million social media messages in China with listed firms and construct a measure of individual stock sentiment based on the tone of those messages. We document that positive investor sentiment predicts higher stock risk-adjusted returns in the very short term followed by price reversals. This association between stock sentiment and stock returns is not explained by observable stock characteristics, unobservable time-invariant characteristics, market-wide sentiment, overreaction to news, or changing investor attention. Consistent with theories of investor sentiment, we find that the link between sentiment and stock returns is mainly driven by positive sentiment and non-professional investors. Finally, exploiting a unique feature of the Chinese stock market, we are able to isolate the causal effect of sentiment on stock returns from confounding factors.
Keywords: Investor sentiment; Stock returns; Social media; Investor attention; News sentiment (search for similar items in EconPapers)
JEL-codes: G11 G12 G41 (search for similar items in EconPapers)
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S1057521920302179
Full text for ScienceDirect subscribers only
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:eee:finana:v:72:y:2020:i:c:s1057521920302179
DOI: 10.1016/j.irfa.2020.101573
Access Statistics for this article
International Review of Financial Analysis is currently edited by B.M. Lucey
More articles in International Review of Financial Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().