Developing a Trading System for the Stock Market Using Sentiment Labeling 


Vol. 47,  No. 11, pp. 1900-1907, Nov.  2022
10.7840/kics.2022.47.11.1900


PDF
  Abstract

Most of the studies predicting the direction of the stock market have been used structured data. This study analyzed the sentiment of market participants using unstructured data (news and community data) that were not previously used and developed an sentiment labeling-based trading system using them. In order to build an sentiment dictionary suitable for the stock market when constructing an sentiment dictionary, a new sentiment dictionary was constructed using cosine similarity. News data were used to represent the sensibilities of individual stocks, and community data were used to represent the sensibilities of individual investors. News and community data were combined to comprehensively consider individual stock sentiment and individual investor sentiment. As a result of the experiment, it was confirmed that the sentiment labeling method performed better than the Up/Down labeling method, which is a method of predicting fluctuations in stock prices. Through this study, it was confirmed that using sentiment analysis of the market and individual investors can make excess profits in the stock market.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Related Articles
  Cite this article

[IEEE Style]

M. Park and J. Kim, "Developing a Trading System for the Stock Market Using Sentiment Labeling," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 11, pp. 1900-1907, 2022. DOI: 10.7840/kics.2022.47.11.1900.

[ACM Style]

Meyong-seok Park and Jaeyun Kim. 2022. Developing a Trading System for the Stock Market Using Sentiment Labeling. The Journal of Korean Institute of Communications and Information Sciences, 47, 11, (2022), 1900-1907. DOI: 10.7840/kics.2022.47.11.1900.

[KICS Style]

Meyong-seok Park and Jaeyun Kim, "Developing a Trading System for the Stock Market Using Sentiment Labeling," The Journal of Korean Institute of Communications and Information Sciences, vol. 47, no. 11, pp. 1900-1907, 11. 2022. (https://doi.org/10.7840/kics.2022.47.11.1900)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880