Mechanically Extracted Company Signals and their Impact on Stock and Credit Markets

Ferdinand Graf ()
Additional contact information
Ferdinand Graf: Department of Economics, University of Konstanz, Germany

No 2011-18, Working Paper Series of the Department of Economics, University of Konstanz from Department of Economics, University of Konstanz

Abstract: I analyze company news from Reuters with the 'General Inquirer' and relate measures of positive sentiment, negative sentiment and disagreement to abnormal stock returns, stock and option trading volume, the volatility spread and the CDS spread. I test hypotheses derived from market microstructure models. Consistent with these models, sentiment and disagreement are strongly related to trading volume. Moreover, sentiment and disagreement might be used to predict stock returns, trading volume and volatility. Trading strategies based on positive and negative sentiment are profitable if the transaction costs are moderate, indicating that stock markets are not fully efficient.

Keywords: Content Analysis; Company News; Market Microstructure (search for similar items in EconPapers)
JEL-codes: G12 G14 (search for similar items in EconPapers)
Pages: 41 pages
Date: 2011-05-31
New Economics Papers: this item is included in nep-mst
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)

Downloads: (external link)
http://www.uni-konstanz.de/FuF/wiwi/workingpaperseries/WP_18-11-Graf.pdf (application/pdf)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:knz:dpteco:1118

Ordering information: This working paper can be ordered from
https://www.wiwi.uni-konstanz.de/en

Access Statistics for this paper

More papers in Working Paper Series of the Department of Economics, University of Konstanz from Department of Economics, University of Konstanz Contact information at EDIRC.
Bibliographic data for series maintained by Office Ursprung ( this e-mail address is bad, please contact ).