Change search
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf
Forecasting Stock Market Movement Direction Using Sentiment Analysis and Support Vector Machine
Stockholm University, Faculty of Social Sciences, Stockholm Business School. University of Chinese Academy of Science, China.
Number of Authors: 32019 (English)In: IEEE Systems Journal, ISSN 1932-8184, E-ISSN 1937-9234, Vol. 13, no 1, p. 760-770Article in journal (Refereed) Published
Abstract [en]

Investor sentiment plays an important role on the stock market. User-generated textual content on the Internet provides a precious source to reflect investor psychology and predicts stock prices as a complement to stock market data. This paper integrates sentiment analysis into a machine learning method based on support vector machine. Furthermore, we take the day-of-week effect into consideration and construct more reliable and realistic sentiment indexes. Empirical results illustrate that the accuracy of forecasting the movement direction of the SSE 50 Index can be as high as 89.93% with a rise of 18.6% after introducing sentiment variables. And, meanwhile, our model helps investors make wiser decisions. These findings also imply that sentiment probably contains precious information about the asset fundamental values and can be regarded as one of the leading indicators of the stock market.

Place, publisher, year, edition, pages
2019. Vol. 13, no 1, p. 760-770
Keywords [en]
Day-of-week effect, decision making, sentiment analysis, stock markets, text mining
National Category
Computer and Information Sciences Electrical Engineering, Electronic Engineering, Information Engineering Economics and Business
Identifiers
URN: urn:nbn:se:su:diva-167646DOI: 10.1109/JSYST.2018.2794462ISI: 000459697700072OAI: oai:DiVA.org:su-167646DiVA, id: diva2:1303036
Available from: 2019-04-08 Created: 2019-04-08 Last updated: 2019-04-08Bibliographically approved

Open Access in DiVA

No full text in DiVA

Other links

Publisher's full text

Search in DiVA

By author/editor
Wu, Desheng Dash
By organisation
Stockholm Business School
In the same journal
IEEE Systems Journal
Computer and Information SciencesElectrical Engineering, Electronic Engineering, Information EngineeringEconomics and Business

Search outside of DiVA

GoogleGoogle Scholar

doi
urn-nbn

Altmetric score

doi
urn-nbn
Total: 40 hits
CiteExportLink to record
Permanent link

Direct link
Cite
Citation style
  • apa
  • ieee
  • modern-language-association-8th-edition
  • vancouver
  • Other style
More styles
Language
  • de-DE
  • en-GB
  • en-US
  • fi-FI
  • nn-NO
  • nn-NB
  • sv-SE
  • Other locale
More languages
Output format
  • html
  • text
  • asciidoc
  • rtf