Chinese Analyst Report Sentiment and Stock Market Responses

Summary

This study applies natural language processing to Chinese analyst reports, using a customized BERT model to classify their tone as positive, neutral, or negative. It examines whether report sentiment helps explain subsequent stock outcomes, including excess returns, volatility, and trading volume. The analysis focuses on the Chinese equity market and treats report language as a measurable market signal.

The reported associations differ by sentiment direction. Strongly positive reports are linked to higher excess returns and intraday volatility, while strongly negative reports are linked to greater volatility and trading volume alongside lower future excess returns. The reported effects are larger for positive sentiment than for negative sentiment. These findings suggest that report tone may carry information about both returns and trading activity, but the supplied description does not specify the sample period, portfolio or trading rules, or controls used. Predictive associations therefore should not be taken as proof that a strategy based on the classifications would earn net profits.

Key ideas

• A customized Chinese-language BERT model classifies analyst reports by sentiment.
• The study relates report sentiment to excess returns, volatility, and trading volume.
• Strong positive sentiment is associated with higher excess returns and intraday volatility.
• Strong negative sentiment is associated with higher volatility and volume, but lower future excess returns.
• The described results concern the Chinese stock market and do not establish net strategy profitability.

Tags

# Analyst Reports and Stock Performance: Evidence from the Chinese Market


# Analyst Reports and Stock Performance: Evidence from the Chinese Market









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.

Shown in full with attribution under the source's licence. Licence: abstract CC0

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.