Investor sentiment;
Event study;
Social media;
Micro-blogs;
Natural language processing;
C55;
G14;
G17;
D O I:
10.1007/s42521-023-00102-z
中图分类号:
学科分类号:
摘要:
We classify the sentiment of a large sample of StockTwits messages as bullish, bearish or neutral, and create a stock-aggregate daily sentiment polarity measure. Polarity is positively associated with contemporaneous stock returns. On average, polarity is not able to predict next-day stock returns. But when we condition on specific events, defined as sudden peaks of message volume, polarity has predictive power on abnormal returns. Polarity-sorted portfolios illustrate the economic relevance of our sentiment measure.