Analyst Reports and Stock Performance: Evidence from the Chinese Market

TL;DR

This paper uses NLP and deep learning to analyze Chinese analyst reports, demonstrating that report sentiment significantly predicts stock volatility, returns, and trading volume, with positive sentiment having a stronger impact.

Contribution

It introduces a customized BERT model for Chinese text sentiment analysis and provides empirical evidence of its predictive power on stock market variables in China.

Findings

Positive sentiment reports increase excess returns and volatility.

Negative sentiment reports also increase volatility and trading volume.

Positive sentiment has a stronger effect than negative sentiment.

Abstract

This article applies natural language processing (NLP) to extract and quantify textual information to predict stock performance. Using an extensive dataset of Chinese analyst reports and employing a customized BERT deep learning model for Chinese text, this study categorizes the sentiment of the reports as positive, neutral, or negative. The findings underscore the predictive capacity of this sentiment indicator for stock volatility, excess returns, and trading volume. Specifically, analyst reports with strong positive sentiment will increase excess return and intraday volatility, and vice versa, reports with strong negative sentiment also increase volatility and trading volume, but decrease future excess return. The magnitude of this effect is greater for positive sentiment reports than for negative sentiment reports. This article contributes to the empirical literature on sentiment analysis and the response of the stock market to news in the Chinese stock market.