Analyzing the correlation between online texts and stock price movements at micro-level using machine learning

František Dařena, Jonas Petrovsky (jonas.petrovsky@mendelu.cz), Jan Zizka (jan.zizka@mendelu.cz) and Jan Prichystal (jan.prichystal@mendelu.cz)
Additional contact information
Jonas Petrovsky: Department of Informatics, Faculty of Business and Economics, Mendel University in Brno, Zemedelska 1, 613 00 Brno, Czech Republic
Jan Zizka: Department of Informatics, Faculty of Business and Economics, Mendel University in Brno, Zemedelska 1, 613 00 Brno, Czech Republic
Jan Prichystal: Department of Informatics, Faculty of Business and Economics, Mendel University in Brno, Zemedelska 1, 613 00 Brno, Czech Republic

No 2016-67, MENDELU Working Papers in Business and Economics from Mendel University in Brno, Faculty of Business and Economics

Abstract: The paper presents the result of experiments that were designed with the goal of revealing the correlation between texts published in online environments (Yahoo! Finance, Facebook, and Twitter) and changes in stock prices of the corresponding companies at a micro level. The association between lexicon detected sentiment and stock prices movements was not confirmed. It was, however, possible to reveal a dependence with application of machine learning based classification. From the experiments it was obvious that the data preparation procedure had a substantial impact on the results. Thus, different stock prices smoothing, lags between documents’ release and related stock price changes, five levels of a minimal stock price change, three different weighting schemes for structured document representation, and six classifiers were studied. It has been shown that at least a part of stock price movements is associated to the texts with a proper combination of these parameters.

Keywords: Stock price movements; machine learning; classification; textual documents; sentiment (search for similar items in EconPapers)
JEL-codes: C38 G17 (search for similar items in EconPapers)
Pages: 26
Date: 2016-12
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://ftp.mendelu.cz/RePEc/men/wpaper/67_2016.pdf Full text (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:men:wpaper:67_2016

Access Statistics for this paper

More papers in MENDELU Working Papers in Business and Economics from Mendel University in Brno, Faculty of Business and Economics Contact information at EDIRC.
Bibliographic data for series maintained by Luděk Kouba (kouba@mendelu.cz).