Tales of Emotion and Stock in China: Volatility, Causality and Prediction

TL;DR

This study analyzes how online emotions expressed on Weibo influence and can predict Chinese stock market fluctuations, revealing that emotional volatility among inexperienced investors significantly impacts market dynamics.

Contribution

It introduces a novel prediction model leveraging online emotional data from Weibo, outperforming traditional financial models in forecasting Chinese stock market attributes.

Findings

Inexperienced investors with high emotional volatility are more sensitive to market changes.

Online emotions like disgust, joy, sadness, and fear can predict stock market attributes.

The proposed prediction model outperforms baseline models in real-world scenarios.

Abstract

How the online social media, like Twitter or its variant Weibo, interacts with the stock market and whether it can be a convincing proxy to predict the stock market have been debated for years, especially for China. As the traditional theory in behavioral finance states, the individual emotions can influence decision-makings of investors, it is reasonable to further explore these controversial topics systematically from the perspective of online emotions, which are richly carried by massive tweets in social media. Through thorough studies on over 10 million stock-relevant tweets and 3 million investors from Weibo, it is revealed that inexperienced investors with high emotional volatility are more sensible to the market fluctuations than the experienced or institutional ones, and their dominant occupation also indicates that the Chinese market might be more emotional as compared to its western counterparts. Then both correlation analysis and causality test demonstrate that five attributes of the stock market in China can be competently predicted by various online emotions, like disgust, joy, sadness and fear. Specifically, the presented prediction model significantly outperforms the baseline model, including the one taking purely financial time series as input features, on predicting five attributes of the stock market under the $K$-means discretization. We also employ this prediction model in the scenario of realistic online application and its performance is further testified.