When machines read the news: Using automated text analytics to quantify high frequency news-implied market reactions

Groß-Klußmann, Axel; Hautsch, Nikolaus

doi:10.1016/j.jempfin.2010.11.009

Cited by 243 publications

(119 citation statements)

References 34 publications

Supporting

Mentioning

111

Contrasting

Unclassified

Order By: Relevance

“…In the following, the notation S denotes this combined measure. The correlation between surprise and θ is surprisingly low and the scatterplot is very noisy 3 . By restricting to Medium and High importance news, the Spearman correlation coefficient between surprise and θ is 0.34 and different from zero in a statistically significant way.…”

Section: A Activity Jumps and News Surprisementioning

confidence: 99%

“…It seems that even this very simple measure of surprise, that does not take into account the specificity of each indicator, is nevertheless able to capture some relevant information. 3 One could try to reduce this noise by normalizing the surprise indicator by the historical standard deviation, thus taking into account the typical uncertainty of the surprise of each news. This however would require much longer time series in order to have enough observations for each type of news.…”

Section: A Activity Jumps and News Surprisementioning

confidence: 99%

“…The dynamics of asset prices, in fact, is affected by the arrival of exogenous news, which modifies the valuation of the fair price of the asset, and by the arrival of endogenously generated events (e.g. trades, orders, and price changes) in reaction to past events [1][2][3]. Disentangling and quantifying the relative importance of these two drivers have been debated widely in the last half century, since the formalization of the Efficient Market Hypothesis.…”

Section: Introductionmentioning

confidence: 99%

“…Refs. [7] and [21] explored the role of news in high-frequency volatility and order book dynamics. A more extensive survey of the literature on news impact can be found in [22].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Modeling foreign exchange market activity around macroeconomic news: Hawkes-process approach

2015

View full text Add to dashboard Cite

We present a Hawkes model approach to foreign exchange market in which the high frequency price dynamics is affected by a self exciting mechanism and an exogenous component, generated by the pre-announced arrival of macroeconomic news. By focusing on time windows around the news announcement, we find that the model is able to capture the increase of trading activity after the news, both when the news has a sizeable effect on volatility and when this effect is negligible, either because the news in not important or because the announcement is in line with the forecast by analysts. We extend the model by considering non-causal effects, due to the fact that the existence of the news (but not its content) is known by the market before the announcement.

show abstract

Section: A Activity Jumps and News Surprisementioning

confidence: 99%

Section: A Activity Jumps and News Surprisementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…Refs. [7] and [21] explored the role of news in high-frequency volatility and order book dynamics. A more extensive survey of the literature on news impact can be found in [22].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Modeling foreign exchange market activity around macroeconomic news: Hawkes-process approach

2015

View full text Add to dashboard Cite

show abstract

“…Groß- Klußmann and Hautsch (2011) analyse in a high frequency context market reactions to the intraday stock specific "Reuters NewsScope Sentiment" engine. Their findings support the hypothesis of news influence on volatility and trading volume, but are in contrast to our study based on a single news source and confined to a limited number of assets for which high frequency data are available.…”

Section: Introductionmentioning

confidence: 99%

Distillation of News Flow Into Analysis of Stock Reactions

Zhang

Härdle

Chen

et al. 2016

Journal of Business & Economic Statistics

View full text Add to dashboard Cite

News carry information of market moves. The gargantuan plethora of opinions, facts and tweets on financial business offers the opportunity to test and analyze the * This research was supported by the Deutsche Forschungsgemeinschaft through the SFB 649 'Economic Risk', Humbold-Universität zu Berlin. We like to thank the Research Data Center (RDC) for the data used in this study. We would also like to thank the International Research Training Group (IRTG) 1792.1 influence of such text sources on future directions of stocks. It also creates though the necessity to distill via statistical technology the informative elements of this prodigious and indeed colossal data source. Using mixed text sources from professional platforms, blog fora and stock message boards we distill via different lexica sentiment variables. These are employed for an analysis of stock reactions: volatility, volume and returns. An increased (negative) sentiment will influence volatility as well as volume. This influence is contingent on the lexical projection and different across GICS sectors. Based on review articles on 100 S&P 500 constituents for the period of October 20, 2009 to October 13, 2014 we project into BL, MPQA, LM lexica and use the distilled sentiment variables to forecast individual stock indicators in a panel context. Exploiting different lexical projections, and using different stock reaction indicators we aim at answering the following research questions: (i) Are the lexica consistent in their analytic ability to produce stock reaction indicators, including volatility, detrended log trading volume and return? (ii) To which degree is there an asymmetric response given the sentiment scales (positive v.s. negative)? (iii) Are the news of high attention firms diffusing faster and result in more timely and efficient stock reaction? (iv) Is there a sector specific reaction from the distilled sentiment measures? We find there is significant incremental information in the distilled news flow. The three lexica though are not consistent in their analytic ability. Based on confidence bands an asymmetric, attention-specific and sector-specific response of stock reactions is diagnosed.

show abstract