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

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

Research output: Contribution to journalArticlepeer-review

98 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 languageEnglish
Pages (from-to)791-830
Number of pages40
JournalJournal of Business Finance and Accounting
Volume41
Issue number7-8
DOIs
StatePublished - 1 Sep 2014

Keywords

  • Computational linguistics
  • Event study
  • Information leakage
  • Market reaction
  • News events

Fingerprint

Dive into the research topics of 'News or noise? Using twitter to identify and understand company-specific news flow'. Together they form a unique fingerprint.

Cite this