Market Reaction to News and Investor Attention in Real Time
50 Pages Posted: 31 Jul 2017 Last revised: 16 Aug 2017
Date Written: August 15, 2017
This paper develops a new framework to study investor attention in real time at high frequency. Using information retrieval approach, we construct a proxy for attention from the Twitter messages of financial experts, hedge funds and portfolio managers around the release of unscheduled news announcements. We then examine how markets react to new information in the absence and presence of attention. On implementing our methodology with high-frequency data for large-cap U.S. stocks, we find evidence that news events receiving attention on social media lead to large and persistent changes in trading activity, volatility and price jumps. When the attention is limited, however, the news effects on such trading patterns tend to be smaller and vanish quickly. With respect to reaction timing, we find that approximately one fourth of the news stories arrive first on Twitter before being reported by Bloomberg newswire. This result suggests that movements prior to news releases may not be explained only by private information, but could also be related to timestamp delays. We control for such potential biases by incorporating attention and correcting newswire timestamps. This adjustment considerably eliminates the pre-announcement effects in the data.
Keywords: Investor attention, News announcements, Stock returns, High-frequency data, Big data, Volatility, Jumps, Social media, Textual analysis, Information retrieval
JEL Classification: D83, G12, G14
Suggested Citation: Suggested Citation