Social Media Analysts' Skills: Insights from Text-implied Beliefs

80 Pages Posted: 29 Mar 2021 Last revised: 16 Mar 2024

See all articles by Chukwuma Dim

Chukwuma Dim

George Washington University

Date Written: December 17, 2020

Abstract

This paper analyzes the extent to which nonprofessional social media investment analysts (SMAs) form correct beliefs about stock returns. Contrary to the wisdom-of-the-crowd view, over half of the SMAs are skilled and express beliefs that correctly align with future returns. There is substantial skill heterogeneity among the SMAs: some 13% high-type SMAs produce a one-week three-factor alpha of 61 bps, while the remaining 87% generate only 6 bps. Firm and industry specializations are the high type's distinctive traits. Although SMAs extrapolate and herd, their expectations are not systematically wrong. Consistent with theory, the extrapolation and herding intensities depend on SMAs' skills.

Keywords: Nonprofessional analysts, Expectation formation, Social networks, Social finance, Machine learning, Textual analysis

JEL Classification: G11, G12, G14

Suggested Citation

Dim, Chukwuma, Social Media Analysts' Skills: Insights from Text-implied Beliefs (December 17, 2020). Available at SSRN: https://ssrn.com/abstract=3813252 or http://dx.doi.org/10.2139/ssrn.3813252

Chukwuma Dim (Contact Author)

George Washington University ( email )

2121 I Street NW
Washington, DC 20052
United States

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

Paper statistics

Downloads
1,344
Abstract Views
4,849
Rank
27,741
PlumX Metrics