Machine news and volatility: The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series

David E. Allen, Michael J. McAleer, Abhay K. Singh

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

Abstract

This chapter features an analysis of the relationship between the volatility of the Dow Jones Industrial Average (DJIA) Index and a sentiment news series using daily data obtained from the Thomson Reuters News Analytics (TRNA) provided by The Securities Industry Research Center of the Asia Pacific. The expansion of online financial news sources, such as Internet news and social media sources, provides instantaneous access to financial news. Commercial agencies have started developing their own filtered financial news feeds, which are used by investors and traders to support their algorithmic trading strategies. In this chapter, we use a high-frequency sentiment series, developed by TRNA, to construct a series of daily sentiment scores for DJIA stock index component companies. A variety of forms of this measure, namely, basic scores, absolute values of the series, squared values of the series, and the first differences of the series, are used to estimate three standard volatility models, namely, GARCH (Generalized Autoregressive Conditional Heteroscedastic), EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasctic), and GJR (Glosten, Jagganathan and Rundle (1993)). We use these alternative daily DJIA market sentiment scores to examine the relationship between financial news sentiment scores and the volatility of the DJIA return series. We demonstrate how this calibration of machine-filtered news can improve volatility measures.
LanguageEnglish
Title of host publicationThe handbook of high frequency trading
EditorsGreg N. Gregoriou
Place of PublicationLondon
PublisherElsevier
Chapter19
Pages327-344
Number of pages18
ISBN (Electronic)9780128023624
ISBN (Print)9780128022054
DOIs
Publication statusPublished - 2015
Externally publishedYes

Fingerprint

Sentiment
News
World Wide Web
Asia-Pacific
Algorithmic trading
News media
Calibration
Market sentiment
Research center
Trading strategies
Volatility models
Traders
Stock index
Industry
Investors
Social media

Keywords

  • Conditional volatility models
  • DJIA
  • Sentiment scores
  • TRNA

Cite this

Allen, D. E., McAleer, M. J., & Singh, A. K. (2015). Machine news and volatility: The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series. In G. N. Gregoriou (Ed.), The handbook of high frequency trading (pp. 327-344). London: Elsevier. https://doi.org/10.1016/B978-0-12-802205-4.00019-1
Allen, David E. ; McAleer, Michael J. ; Singh, Abhay K. / Machine news and volatility : The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series. The handbook of high frequency trading. editor / Greg N. Gregoriou. London : Elsevier, 2015. pp. 327-344
@inbook{936652ada2a5424fa8b3f412462fe771,
title = "Machine news and volatility: The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series",
abstract = "This chapter features an analysis of the relationship between the volatility of the Dow Jones Industrial Average (DJIA) Index and a sentiment news series using daily data obtained from the Thomson Reuters News Analytics (TRNA) provided by The Securities Industry Research Center of the Asia Pacific. The expansion of online financial news sources, such as Internet news and social media sources, provides instantaneous access to financial news. Commercial agencies have started developing their own filtered financial news feeds, which are used by investors and traders to support their algorithmic trading strategies. In this chapter, we use a high-frequency sentiment series, developed by TRNA, to construct a series of daily sentiment scores for DJIA stock index component companies. A variety of forms of this measure, namely, basic scores, absolute values of the series, squared values of the series, and the first differences of the series, are used to estimate three standard volatility models, namely, GARCH (Generalized Autoregressive Conditional Heteroscedastic), EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasctic), and GJR (Glosten, Jagganathan and Rundle (1993)). We use these alternative daily DJIA market sentiment scores to examine the relationship between financial news sentiment scores and the volatility of the DJIA return series. We demonstrate how this calibration of machine-filtered news can improve volatility measures.",
keywords = "Conditional volatility models, DJIA, Sentiment scores, TRNA",
author = "Allen, {David E.} and McAleer, {Michael J.} and Singh, {Abhay K.}",
year = "2015",
doi = "10.1016/B978-0-12-802205-4.00019-1",
language = "English",
isbn = "9780128022054",
pages = "327--344",
editor = "Gregoriou, {Greg N.}",
booktitle = "The handbook of high frequency trading",
publisher = "Elsevier",
address = "Netherlands",

}

Allen, DE, McAleer, MJ & Singh, AK 2015, Machine news and volatility: The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series. in GN Gregoriou (ed.), The handbook of high frequency trading. Elsevier, London, pp. 327-344. https://doi.org/10.1016/B978-0-12-802205-4.00019-1

Machine news and volatility : The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series. / Allen, David E.; McAleer, Michael J.; Singh, Abhay K.

The handbook of high frequency trading. ed. / Greg N. Gregoriou. London : Elsevier, 2015. p. 327-344.

Research output: Chapter in Book/Report/Conference proceedingChapterResearchpeer-review

TY - CHAP

T1 - Machine news and volatility

T2 - The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series

AU - Allen, David E.

AU - McAleer, Michael J.

AU - Singh, Abhay K.

PY - 2015

Y1 - 2015

N2 - This chapter features an analysis of the relationship between the volatility of the Dow Jones Industrial Average (DJIA) Index and a sentiment news series using daily data obtained from the Thomson Reuters News Analytics (TRNA) provided by The Securities Industry Research Center of the Asia Pacific. The expansion of online financial news sources, such as Internet news and social media sources, provides instantaneous access to financial news. Commercial agencies have started developing their own filtered financial news feeds, which are used by investors and traders to support their algorithmic trading strategies. In this chapter, we use a high-frequency sentiment series, developed by TRNA, to construct a series of daily sentiment scores for DJIA stock index component companies. A variety of forms of this measure, namely, basic scores, absolute values of the series, squared values of the series, and the first differences of the series, are used to estimate three standard volatility models, namely, GARCH (Generalized Autoregressive Conditional Heteroscedastic), EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasctic), and GJR (Glosten, Jagganathan and Rundle (1993)). We use these alternative daily DJIA market sentiment scores to examine the relationship between financial news sentiment scores and the volatility of the DJIA return series. We demonstrate how this calibration of machine-filtered news can improve volatility measures.

AB - This chapter features an analysis of the relationship between the volatility of the Dow Jones Industrial Average (DJIA) Index and a sentiment news series using daily data obtained from the Thomson Reuters News Analytics (TRNA) provided by The Securities Industry Research Center of the Asia Pacific. The expansion of online financial news sources, such as Internet news and social media sources, provides instantaneous access to financial news. Commercial agencies have started developing their own filtered financial news feeds, which are used by investors and traders to support their algorithmic trading strategies. In this chapter, we use a high-frequency sentiment series, developed by TRNA, to construct a series of daily sentiment scores for DJIA stock index component companies. A variety of forms of this measure, namely, basic scores, absolute values of the series, squared values of the series, and the first differences of the series, are used to estimate three standard volatility models, namely, GARCH (Generalized Autoregressive Conditional Heteroscedastic), EGARCH (Exponential Generalized Autoregressive Conditional Heteroscedasctic), and GJR (Glosten, Jagganathan and Rundle (1993)). We use these alternative daily DJIA market sentiment scores to examine the relationship between financial news sentiment scores and the volatility of the DJIA return series. We demonstrate how this calibration of machine-filtered news can improve volatility measures.

KW - Conditional volatility models

KW - DJIA

KW - Sentiment scores

KW - TRNA

UR - https://www.scopus.com/inward/record.uri?eid=2-s2.0-84941076830&doi=10.1016%2fB978-0-12-802205-4.00019-1&partnerID=40&md5=68f475eb1e468398d02fe0a302697e77

U2 - 10.1016/B978-0-12-802205-4.00019-1

DO - 10.1016/B978-0-12-802205-4.00019-1

M3 - Chapter

SN - 9780128022054

SP - 327

EP - 344

BT - The handbook of high frequency trading

A2 - Gregoriou, Greg N.

PB - Elsevier

CY - London

ER -

Allen DE, McAleer MJ, Singh AK. Machine news and volatility: The Dow Jones Industrial Average and the TRNA real-time high-frequency sentiment series. In Gregoriou GN, editor, The handbook of high frequency trading. London: Elsevier. 2015. p. 327-344 https://doi.org/10.1016/B978-0-12-802205-4.00019-1