News or noise? Using twitter to identify and understand company-specific news flow

Timm O. Sprenger; Philipp G. Sandner; Andranik Tumasjan; Isabell M. Welpe

doi:10.1111/jbfa.12086

News or noise? Using twitter to identify and understand company-specific news flow

Timm O. Sprenger, Philipp G. Sandner, Andranik Tumasjan, Isabell M. Welpe

Chair of Strategy and Organization

Technical University of Munich

Research output: Contribution to journal › Article › peer-review

109 Scopus citations

Abstract

This study presents a methodology for identifying a broad range of real-world news events based on microblogging messages. Applying computational linguistics to a unique dataset of more than 400,000 S&P 500 stock-related Twitter messages, we distinguish between good and bad news and demonstrate that the returns prior to good news events are more pronounced than for bad news events. We show that the stock market impact of news events differs substantially across different categories.

Original language	English
Pages (from-to)	791-830
Number of pages	40
Journal	Journal of Business Finance and Accounting
Volume	41
Issue number	7-8
DOIs	https://doi.org/10.1111/jbfa.12086
State	Published - 1 Sep 2014

Keywords

Computational linguistics
Event study
Information leakage
Market reaction
News events

Access to Document

10.1111/jbfa.12086

Cite this

@article{01424d167dab4e549b6787365ea0af5d,

title = "News or noise? Using twitter to identify and understand company-specific news flow",

abstract = "This study presents a methodology for identifying a broad range of real-world news events based on microblogging messages. Applying computational linguistics to a unique dataset of more than 400,000 S&P 500 stock-related Twitter messages, we distinguish between good and bad news and demonstrate that the returns prior to good news events are more pronounced than for bad news events. We show that the stock market impact of news events differs substantially across different categories.",

keywords = "Computational linguistics, Event study, Information leakage, Market reaction, News events",

author = "Sprenger, {Timm O.} and Sandner, {Philipp G.} and Andranik Tumasjan and Welpe, {Isabell M.}",

note = "Publisher Copyright: {\textcopyright} 2014 John Wiley & Sons Ltd.",

year = "2014",

month = sep,

day = "1",

doi = "10.1111/jbfa.12086",

language = "English",

volume = "41",

pages = "791--830",

journal = "Journal of Business Finance and Accounting",

issn = "0306-686X",

publisher = "Wiley-Blackwell Publishing Ltd",

number = "7-8",

}

TY - JOUR

T1 - News or noise? Using twitter to identify and understand company-specific news flow

AU - Sprenger, Timm O.

AU - Sandner, Philipp G.

AU - Tumasjan, Andranik

AU - Welpe, Isabell M.

PY - 2014/9/1

Y1 - 2014/9/1

N2 - This study presents a methodology for identifying a broad range of real-world news events based on microblogging messages. Applying computational linguistics to a unique dataset of more than 400,000 S&P 500 stock-related Twitter messages, we distinguish between good and bad news and demonstrate that the returns prior to good news events are more pronounced than for bad news events. We show that the stock market impact of news events differs substantially across different categories.

AB - This study presents a methodology for identifying a broad range of real-world news events based on microblogging messages. Applying computational linguistics to a unique dataset of more than 400,000 S&P 500 stock-related Twitter messages, we distinguish between good and bad news and demonstrate that the returns prior to good news events are more pronounced than for bad news events. We show that the stock market impact of news events differs substantially across different categories.

KW - Computational linguistics

KW - Event study

KW - Information leakage

KW - Market reaction

KW - News events

UR - http://www.scopus.com/inward/record.url?scp=84907887240&partnerID=8YFLogxK

U2 - 10.1111/jbfa.12086

DO - 10.1111/jbfa.12086

M3 - Article

AN - SCOPUS:84907887240

SN - 0306-686X

VL - 41

SP - 791

EP - 830

JO - Journal of Business Finance and Accounting

JF - Journal of Business Finance and Accounting

IS - 7-8

ER -

News or noise? Using twitter to identify and understand company-specific news flow

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this