| Authors |
Dim |
| Year |
2022 |
| Type |
Working Paper |
| Abstract |
This paper uses machine learning to infer nonprofessional social media investment analysts' (SMAs) beliefs from their opinions on individual stocks. SMAs' average beliefs predict future abnormal returns and earnings surprises. However, there exists substantial heterogeneity in SMAs' ability to form beliefs that yield investment value. Some 13% high-skilled SMAs form beliefs that yield a sizeable one-week three-factor alpha of 61 bps, while the remaining 87% low-skilled SMAs generate only 6 bps. Firm and industry specializations are the most distinctive characteristics of high-skilled SMAs. When forming beliefs, SMAs extrapolate from past returns and herd on the consensus view of their peers. However, these seemingly behavioral biases do not result in systematically wrong beliefs. |
| Keywords |
Nonprofessional analysts, belief formation, investor skill, market efficiency, herding, extrapolation, machine learning, natural language processing |
| URL |
https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3813252 |
| Tags |
Archival Empirical |
Asset Pricing, Trading Volume and Market Efficiency |
Financing- and Investment Decisions (Individual) |
Media and Textual Analysis |
Social Network Structure
|