【讲座时间】：3月8日（周五）上午9:00-11:00
【讲座地点】：北京大学经济学院，107会议室
【讲座标题】：Measuring China’s Stock Market Sentiment
【摘要】：This paper develops textual sentiment measures for China's stock market by extracting the tone of 60 million messages posted on a major online investor forum in China from 2008 to 2018. We extract the textual information from these messages by employing both conventional dictionary-based methods using a customized word-list, and supervised machine-learning methods (support vector machine and convolutional neural network), which rely on a unique training sample with labeled messages. The market-wide textual sentiment index is constructed as the average of message-level sentiment scores, and the textual disagreement index is constructed as their dispersion. These textual measures allow us to test a range of key predictions of leading behavioral asset pricing models in a unified empirical setting. We find that the textual sentiment can significantly predict market return, exhibiting short-run momentum and long-run reversal. This effect is more pronounced for small stocks, and is stronger under high investor attention and during more volatile periods. In addition, we find that the textual sentiment exerts a significant and asymmetric impact on future volatility. Finally, we document that trading volume is higher when the textual sentiment is unusually high or low, and when there are more differences-of-opinion as measured by our textual disagreement. Based on a large textual dataset, our results provide support for the classical noise-trader theory, the limit-to-arbitrage argument, as well as predictions from limited-attention and disagreement models.
【主讲人】：沈艳（教授）
【主讲人简介】：沈艳，经济学博士，2003年加入北京大学中国经济研究中心，现为北京大学国家发展研究院教授。沈艳教授的研究兴趣是计量经济学在实证领域的应用，近年来集中于文本大数据分析，金融科技发展及监管，农村金融等。沈艳教授目前还担任教育部北京大学人力资本与国家政策研究中心副主任，北京大学互联网金融研究中心副主任，China Economic Journal 副主编，中国数量经济学会常任理事，和多家国际刊物的匿名审稿人。
欢迎感兴趣的老师与同学参加！
北大经济学院金融系
2019年3月5日
