Analyst Reports and Stock Performance: Evidence from the Chinese Market

2024-11-13

arXiv.org

AI Summary

This study investigates the predictive power of analyst report sentiment for stock market performance in China’s A-share market. Leveraging a Chinese-specific BERT model, we perform fine-grained sentiment classification (positive/neutral/negative) on brokerage research reports to construct sentiment indices. Using panel regressions and event-study methodology, we examine their out-of-sample predictive ability for future 1–5-day stock volatility, abnormal returns, and turnover rates. We document, for the first time, significant sentiment asymmetry in the Chinese equity market: positive sentiment exhibits substantially stronger predictive power for abnormal returns and intraday volatility than negative sentiment—on average 37% greater in magnitude. Results remain robust across multiple endogeneity controls (e.g., lagged sentiment, instrumental variables) and extensive sensitivity checks. This work provides novel empirical evidence on the role of textual sentiment in asset pricing within emerging markets and extends the frontier of behavioral finance–NLP interdisciplinary research.

Technology Category

• Natural Language Processing: Sentiment Analysis, Stylistic Analysis, and Argument Mining
• Humans and AI: Brain-Sensing and Analysis
• Cognitive Modeling & Cognitive Systems: Affective Computing

Application Category

• Web Mining and Content Analysis: Sentiment analysis and opinion mining
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Economics, Online Markets and Human Computation: The sharing economy

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.

Problem

• Predict stock performance using NLP and sentiment analysis.
• Analyze Chinese analyst reports to forecast market behavior.
• Measure impact of sentiment on volatility, returns, and trading volume.

Innovation

• Uses NLP to extract and quantify textual information
• Employs customized BERT model for Chinese text
• Predicts stock performance using sentiment analysis