Non-scheduled news arrival and high-frequency stock market dynamics

Curtin University of Technology | August 16, 2012

Evidence from the Australian Securities Exchange.

The high-frequency market reaction to intraday stock-specific news flow is examined over the period January 2000 to November 2011. Data on novelty, relevance, and direction of company-specific news for the ASX50 leading Australian stocks is garnered from the Ravenpack news analytics tool.

Main findings:

  • Unconditional analysis of key variables around 484,440 news items discovers distinct responses in market activity, volatility, bid-ask spreads and returns.
  • Classification of news according to indicated relevance is critical to identify significant effects.
  • Reaction of market activity, volatility and spreads is greatest for negative news.

These findings are confirmed when controlling for market dynamics and cross-dependencies between variables in a high-frequency VAR model.


Market efficiency suggests that all currently available public, and private, information should be reflected in share prices. Market participants should only respond to new information (news), and therefore price movements and trading activity will be strongly influenced by the released of both scheduled and non-scheduled news. However, with the advent of modern technology the flow of news has greatly increased and this makes it costly for market participants to process all asset-specific news. As a result, many participants are starting to rely on preprocessed news analytics provided by news vendors; with such data playing an increasingly important role in the trading of financial assets it seems pertinent to ask whether the indicators of relevance and sentiment are both useful and reliable.

Historically, research in this field has focused on specific and readily quantifiable news events such as scheduled macroeconomic announcements and earnings results. For example, Patell and Wolfson (1984) and Woodruff and Senchak (1988) consider the adjustment of stock prices following earnings and dividend announcements, and find that much of the market adjustment occurs in the first 30 minutes following the announcement. Ederington and Lee (1993, 1995), Becker et al. (1996), Bernanke and Kuttner (2005), Rigobon and Sack (2004), and Smales (2013) are among the many papers that consider the impact of macroeconomic announcements with the confirmation of a dynamic response to the news (surprise) component of data releases that quickly subsides.

More recently, the quantifying of news language, by researchers such as Antweiler and Frank (2004) and Tetlock (2007), has enabled the identification of common patterns in firm responses and market reactions across a wider range of events. In particular, the relevance and sentiment of news has been tested in a variety of market settings. Tetlock el al. (2008) examine whether a quantitative measure of language can be used to predict firms’ earnings and stock returns, and find that negative words in firm-specific news stories forecast low firm earnings. Sinha (2011) gauges the tone of news articles and constructs a measure to predict future returns while Engelberg et al. (2012) find that the negative relation between short sales and future returns is significantly stronger in the presence of news stories containing negative news. Dzielinski (2011) utilizes sentiment signed news to directly compare news and no-news stock returns, finding that positive (negative) news results in above (below) average returns whilst the effect of neutral news is non-distinguishable from the no-news average. Interestingly, Tetlock (2011) also reports that investors react to stale news.

In terms of framework, this paper is most similar to Groß-Klußmann and Hautsch (2011) who examine high-frequency news-implied market reactions on 39 liquid stocks traded on the London Stock Exchange over an 18 month period from January 2007. They observe that trading activity reacts significantly to company-specific news items that are identified as relevant, although they do not consider the importance of directional sentiment indicators.

By providing your personal information and submitting your details, you acknowledge that you have read, understood, and agreed to our Privacy Statement and you accept our Terms and Conditions. We will handle your personal information in compliance with our Privacy Statement. You can exercise your rights of access, rectification, erasure, restriction of processing, data portability, and objection by emailing us at in accordance with the GDPRs. You also are agreeing to receive occasional updates and communications from RavenPack about resources, events, products, or services that may be of interest to you.

Data Insights

Read More