Can a 280-character message explain stock returns? Evidence from South Africa

Kingstone Nyakurukwa,Yudhvir Seetharam

doi:10.1108/mf-12-2021-0598

Abstract

PurposeThe authors examine the contemporaneous and causal association between tweet features (bullishness, message volume and investor agreement) and market features (stock returns, trading volume and volatility) using 140 South African companies and a dataset of firm-level Twitter messages extracted from Bloomberg for the period 1 January 2015 to 31 March 2020.Design/methodology/approachPanel regressions with ticker fixed-effects are used to examine the contemporaneous link between tweet features and market features. To examine the link between the magnitude of tweet features and stock market features, the study uses quantile regression.FindingsNo monotonic relationship is found between the magnitude of tweet features and the magnitude of market features. The authors find no evidence that past values of tweet features can predict forthcoming stock returns using daily data while weekly and monthly data shows that past values of tweet features contain useful information that can predict the future values of stock returns.Originality/valueThe study is among the earlier to examine the association between textual sentiment from social media and market features in a South African context. The exploration of the relationship across the distribution of the stock market features gives new insights away from the traditional approaches which investigate the relationship at the mean.

Highlights

While classical finance postulates that investors are rational and build their portfolios using mean-variance optimisation, behavioural finance suggests that investors are normal individuals who build their portfolios using the behavioural portfolio theory (Statman, 2019)
Using data from 140 listed shares on the main board of the Johannesburg Stock Exchange, we investigate whether tweet features are associated with market features
We seek to address the three objectives below: (1) Determine if firm-level tweet features are contemporaneously associated with stock market features; (2) Determine if the magnitude of tweet features is monotonically related to the magnitude of stock market features; (3) Determine if past values of tweet features contain useful information that could be used to predict future values of stock returns

Summary

Introduction

While classical finance postulates that investors are rational and build their portfolios using mean-variance optimisation, behavioural finance suggests that investors are normal individuals who build their portfolios using the behavioural portfolio theory (Statman, 2019). Behavioural finance proponents have challenged the theoretical underpinnings of the efficient markets hypothesis (EMH) as well as the accompanying empirical evidence by arguing that investors are not perfectly rational and capital markets are not perfectly efficient. One aspect of behavioural finance that has received extensive research in recent times is the role of investor sentiment in financial markets. Black (1986) suggests that irrational investors, called noise traders, are known for not trading on fundamental information but are instead driven by sentiment. Several studies across the developed world, as well as developing countries, have confirmed the importance of investor sentiment in financial markets

Methods

Results

Conclusion