Skip to main navigation Skip to search Skip to main content

Sentiment Analysis of Stock Market Investors and Its Correlation with Stock Price Using Maximum Entropy

  • Liang Xue
  • , Han Wang
  • , Fengling Wang
  • , Huawen Ma*
  • *Corresponding author for this work
  • City University of Macau
  • Guangdong University of Education
  • Chinese Academy of Sciences
  • Beijing Institute of Technology

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

To study the correlation between the sentiment of the stock market investors and the stock price, this paper uses Python web crawler to crawl for 20 representative stocks on the Shanghai Stock Exchange (SSE) with two-year’s data and the comment text of related stocks in Guba (a stock forum at Sina.com). Through the extraction and preprocessing on the crawled data, a classifier model using maximum entropy is built to classify stock-related comments into three sentiment labels for analysis. Eventually the sentiment index of investor is established to compare with the fluctuation of stock price. The comparison shows that there is a correlation between the sentiment index of investor and the volatility of stock price, which is beneficial to help investor monitor public opinion and adopts diverse strategies in the stock market.

Original languageEnglish
Title of host publicationComputer and Information Science, 2021
EditorsRoger Lee
PublisherSpringer Science and Business Media Deutschland GmbH
Pages29-44
Number of pages16
ISBN (Print)9783030794736
DOIs
StatePublished - 2021
Externally publishedYes
Event20th IEEE/ACIS International Summer Semi-Virtual Conference on Computer and Information Science, ICIS 2021 - Shanghai, China
Duration: 23 Jun 202125 Jun 2021

Publication series

NameStudies in Computational Intelligence
Volume985
ISSN (Print)1860-949X
ISSN (Electronic)1860-9503

Conference

Conference20th IEEE/ACIS International Summer Semi-Virtual Conference on Computer and Information Science, ICIS 2021
Country/TerritoryChina
CityShanghai
Period23/06/2125/06/21

Keywords

  • Crawler
  • Machine learning
  • Maximum entropy
  • Sentiment analysis
  • Stock

Fingerprint

Dive into the research topics of 'Sentiment Analysis of Stock Market Investors and Its Correlation with Stock Price Using Maximum Entropy'. Together they form a unique fingerprint.

Cite this