News as sources of jumps in stock returns: Evidence from 21 million news articles for 9000 companies

Material news events can be potentially important sources of jumps in stock returns. We collect 21 million news articles associated with more than 9,000 publicly-traded companies and use textual analyses to derive measures to summarize the news. We find that stock return jumps (including time-variation in jump-size distributions and jump intensity) are significantly related to news flow frequency and content and those effects increase substantially over the last few decades. The sensitivity of jump probability to news is stronger for firms with higher media visibility, analyst coverage, and institutional ownership. This sensitivity also varies across different news categories. The primary working dataset based on Factiva news can be downloaded using this link: https://www.dropbox.com/s/62lt6uq1t4n6gcr/MainData_Factiva_Public.zip?dl=0.