| June 15, 2014
In this study, we examine the impact of company-specific news on individual stock prices.
In this study, we examine the impact of company-specific news on individual stock prices. Specifically, we look at the impact across different news types and sources after controlling for size, industry, or event group. The objective of our study is to generally improve the understanding of news analytics with the results potentially providing valuable input into event trading strategies or creating indicators capturing company sentiment.
Evidence has emerged from both academia and practitioners in support of a causal relationship from news sentiment to changes in asset dynamics. Tetlock (2007) shows that negative sentiment in the WSJ column “Abreast of the Market” is followed by lower market prices and thereafter by a reversal to fundamentals. Using 29 years of data on all publicly traded US firms in the Dow Jones news archive, Tetlock (2010) further finds that public information predicts substantially lower ten-day reversals and higher ten-day volumeinduced momentum in daily returns. Riordan et al. (2012) show that, compared to positive news sentiment, negative sentiment is particularly informative with a bigger impact on high-frequency asset price discovery and liquidity.
Ho et al. (2013) use RavenPack News Analytics to confirm the significant impact of firm-specific news sentiment on intraday volatility persistence, even after controlling for the potential effects of macroeconomic news. Hafez and Xie (2013, 2014) shows that news sentiment indicators aggregated at company level contain predictive power for future stock returns and can be used to enhance trading performance of traditional short-term reversal models.
Although the empirical evidence confirms the causal relationship between news sentiment and asset dynamics, such linkage usually ignores the underlying features of news such as news type or news source. Until now, most research has focused on a small set of sources, including premium news wire services from Dow Jones, Bloomberg, or Thomson Reuters. However, with the exponential growth in web-based news, a solid understanding of the news impact from broader web sources is likely to be of considerable significance.
Another important feature to consider is the impact of news type as this could have an impact on how and at what speed financial market participants react to news. Typically, news can be grouped into five different news types: full-article news, hot-news-flashes, news-flashes, press-releases and tabularmaterial.
As will be discussed in Section 2, different news types indicate differences in timeliness, the nature of information, and the presentation of information; all of which have been shown to affect the process of information dissemination and absorption in the financial market (Firth et al., 2009). By examining the news impact at more granular level, considering news type and news source, we will gain a better understanding of the role news plays in asset dynamics. To this end, we will examine the market response pattern across news types and sources after controlling for company size, industry, and event group, variables that all could potentially affect the price impact of news.
Overall, we find that the market reacts most strongly to hot-news-flashes published by premium newswire services. In addition, news-flashes and full-article news are also found to be more predictive when released through premium newswires, while press-releases are more informative for US stocks when coming from the web. We also find that the broader web sources generally have more predictive power for smaller stocks, while premium newswires cause more market impact for larger stocks.
Please use your business email. If you don't have one, please email us at firstname.lastname@example.org.
We will process your personal data with the purpose of managing your personal account on
RavenPack and offering our services. You can exercise your rights of access, rectification,
erasure, restriction of processing, data portability and objection by emailing us at email@example.com. For more information, you can
Your request has been recorded and a team member will be in touch soon.
We consider incorporating sentiment signals from news, earnings call transcripts, and insider transactions to
boost the risk-adjusted returns, and revive factor performance.
We find stronger, more predictable market reactions when the words of company executives agree with their actions.
We have gathered 12 insights from 2021 research that can be leveraged in 2022.