A retail investor in a cobweb of social networks

Tamara Teplova, Aleksandr Tomtosov and Tatiana Sokolova

PLOS ONE, 2022, vol. 17, issue 12, 1-26

Abstract: In this study, using AI, we empirically examine the irrational behaviour, specifically attention-driven trading and emotion-driven trading such as consensus trading, of retail investors in an emerging stock market. We used a neural network to assess the tone of messages on social media platforms and proposed a novel Hype indicator that integrates metrics of investor attention and sentiment. The sample of messages, which are written in Russian with slang expressions, was retrieved from a unique dataset of social network communication of investors in the Russian stock market. Applying different portfolio designs, we evaluated the effectiveness of the new Hype indicator against the factors of momentum, volatility, and trading volume. We found the possibility of building a profitable trading strategy based on the Hype indicator over a 6-month time horizon. Over short periods, the Hype indicator allows investors to earn more by buying stocks of large companies, and over «longer» periods, this indicator tends to perform better for illiquid stocks of small companies. As consensus trading tends to produce negative returns, the investment strategy of ‘Go against the crowd’ proves rewarding in the medium term of 3 months.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0276924 (text/html)
https://journals.plos.org/plosone/article/file?id= ... 76924&type=printable (application/pdf)

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:plo:pone00:0276924

DOI: 10.1371/journal.pone.0276924

Access Statistics for this article

More articles in PLOS ONE from Public Library of Science
Bibliographic data for series maintained by plosone ().