Media-expressed negative tone and firm-level stock returns

Khurshid Ahmad, Jing Guang Han, Elaine Hutson, Colm Kearney, Sha Liu

Research output: Contribution to journalArticleResearchpeer-review

13 Citations (Scopus)

Abstract

We build a corpus of over 51/2 million news articles on 20 large US firms over the 10-year period from January 2001 to December 2010, and use it to study the time-varying nature of the relation between media-expressed firm-specific tone and firm-level returns. By estimating a series of separate rolling window vector autoregressive (VAR) models for each firm, we show how media-expressed negative tone impacts firm-level returns episodically in ways that vary across firms and over time. We find that firms experience prolonged periods during which media-expressed tone has no effect on returns, and occasional episodes when it has a significant impact. During the significant episodes, its impacts are sometimes quickly reversed and at other times they endure - implying that media comment and analysis can sometimes be sentiment (or noise), but it can also contain value-relevant information or news. Our findings are in general consistent with efficiently functioning markets in which the media assists with the processing of complex information.

Original languageEnglish
Pages (from-to)152-172
Number of pages21
JournalJournal of Corporate Finance
Volume37
DOIs
Publication statusPublished - 1 Apr 2016

Keywords

  • Market efficiency
  • Media-expressed tone, negative sentiment
  • News
  • Textual analysis

Cite this

Ahmad, Khurshid ; Han, Jing Guang ; Hutson, Elaine ; Kearney, Colm ; Liu, Sha. / Media-expressed negative tone and firm-level stock returns. In: Journal of Corporate Finance. 2016 ; Vol. 37. pp. 152-172.
@article{2526283be5224420b09ab5773798e25a,
title = "Media-expressed negative tone and firm-level stock returns",
abstract = "We build a corpus of over 51/2 million news articles on 20 large US firms over the 10-year period from January 2001 to December 2010, and use it to study the time-varying nature of the relation between media-expressed firm-specific tone and firm-level returns. By estimating a series of separate rolling window vector autoregressive (VAR) models for each firm, we show how media-expressed negative tone impacts firm-level returns episodically in ways that vary across firms and over time. We find that firms experience prolonged periods during which media-expressed tone has no effect on returns, and occasional episodes when it has a significant impact. During the significant episodes, its impacts are sometimes quickly reversed and at other times they endure - implying that media comment and analysis can sometimes be sentiment (or noise), but it can also contain value-relevant information or news. Our findings are in general consistent with efficiently functioning markets in which the media assists with the processing of complex information.",
keywords = "Market efficiency, Media-expressed tone, negative sentiment, News, Textual analysis",
author = "Khurshid Ahmad and Han, {Jing Guang} and Elaine Hutson and Colm Kearney and Sha Liu",
year = "2016",
month = "4",
day = "1",
doi = "10.1016/j.jcorpfin.2015.12.014",
language = "English",
volume = "37",
pages = "152--172",
journal = "Journal of Corporate Finance",
issn = "0929-1199",
publisher = "Elsevier",

}

Media-expressed negative tone and firm-level stock returns. / Ahmad, Khurshid; Han, Jing Guang; Hutson, Elaine; Kearney, Colm; Liu, Sha.

In: Journal of Corporate Finance, Vol. 37, 01.04.2016, p. 152-172.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Media-expressed negative tone and firm-level stock returns

AU - Ahmad, Khurshid

AU - Han, Jing Guang

AU - Hutson, Elaine

AU - Kearney, Colm

AU - Liu, Sha

PY - 2016/4/1

Y1 - 2016/4/1

N2 - We build a corpus of over 51/2 million news articles on 20 large US firms over the 10-year period from January 2001 to December 2010, and use it to study the time-varying nature of the relation between media-expressed firm-specific tone and firm-level returns. By estimating a series of separate rolling window vector autoregressive (VAR) models for each firm, we show how media-expressed negative tone impacts firm-level returns episodically in ways that vary across firms and over time. We find that firms experience prolonged periods during which media-expressed tone has no effect on returns, and occasional episodes when it has a significant impact. During the significant episodes, its impacts are sometimes quickly reversed and at other times they endure - implying that media comment and analysis can sometimes be sentiment (or noise), but it can also contain value-relevant information or news. Our findings are in general consistent with efficiently functioning markets in which the media assists with the processing of complex information.

AB - We build a corpus of over 51/2 million news articles on 20 large US firms over the 10-year period from January 2001 to December 2010, and use it to study the time-varying nature of the relation between media-expressed firm-specific tone and firm-level returns. By estimating a series of separate rolling window vector autoregressive (VAR) models for each firm, we show how media-expressed negative tone impacts firm-level returns episodically in ways that vary across firms and over time. We find that firms experience prolonged periods during which media-expressed tone has no effect on returns, and occasional episodes when it has a significant impact. During the significant episodes, its impacts are sometimes quickly reversed and at other times they endure - implying that media comment and analysis can sometimes be sentiment (or noise), but it can also contain value-relevant information or news. Our findings are in general consistent with efficiently functioning markets in which the media assists with the processing of complex information.

KW - Market efficiency

KW - Media-expressed tone, negative sentiment

KW - News

KW - Textual analysis

UR - http://www.scopus.com/inward/record.url?scp=84955247333&partnerID=8YFLogxK

U2 - 10.1016/j.jcorpfin.2015.12.014

DO - 10.1016/j.jcorpfin.2015.12.014

M3 - Article

VL - 37

SP - 152

EP - 172

JO - Journal of Corporate Finance

JF - Journal of Corporate Finance

SN - 0929-1199

ER -