Synergy between stock prices and investor sentiment in social media

Abstract

The underlying assumption of using investor sentiment to predict stock prices, stock market returns, and liquidity is that of synergy between stock prices and investor sentiment. However, this synergistic relationship has received little attention in the literature. This paper investigates the synergistic pattern between stock prices and investor sentiment using social media messages from stock market investors and natural language processing techniques. At the macro level, we reveal extremely significant positive synergy between investor sentiment and stock prices. That is, when a stock price rises, investor sentiment rises, and when a stock price falls, investor sentiment falls. However, this synergy may be reversed or even disappear over a specific time period. Through a segmented measurement of the synergy between stock prices and investor sentiment over the course of a day, we also find that investor sentiment on social media is forward looking. This provides theoretical support for using investor sentiment in stock price prediction. We also examine the effect of lockdowns, the most draconian response to COVID-19, on synergy between stock prices and investor sentiment through causal inference machine learning. Our analysis shows that external anxiety can significantly affect synergy between stock prices and investor sentiment, but this effect can promote either positive or negative synergy. This paper offers a new perspective on stock price forecasting, investor sentiment, behavioral finance, and the impact of COVID-19 on the stock markets.

Keywords

• G40
• G41