Analysis of the effect of headline news in financial market through text categorisation

Satoru Takahashi, Hiroshi Takahashi, Kazuhiko Tsuda

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

In this paper, we analyse the relation between stock-price returns and Headline News. Headline News is a very important source of information in asset management and is sent in large quantities every day. We study the effect of more than 13,000 Headline News sent from Jiji Press. We classify Headline News into three types using text categorisation and analyse the reaction of a stock-price return to each types of news. From our research, we figure out following issues: (1) we make the text categorisation system that has about 80% of classification accuracy, (2) this system can extract effective information to stock-price returns from Headline News and (3) such information is more effective to the small firms.

Original languageEnglish
Pages (from-to)204-209
Number of pages6
JournalInternational Journal of Computer Applications in Technology
Volume35
Issue number2-4
DOIs
Publication statusPublished - 2009 Jun
Externally publishedYes

Fingerprint

Asset management
Financial markets

Keywords

  • Headline news
  • Naïve bayes
  • Text auto categorisation
  • Text mining

ASJC Scopus subject areas

  • Computer Science Applications
  • Electrical and Electronic Engineering
  • Industrial and Manufacturing Engineering
  • Software
  • Information Systems
  • Computer Networks and Communications

Cite this

Analysis of the effect of headline news in financial market through text categorisation. / Takahashi, Satoru; Takahashi, Hiroshi; Tsuda, Kazuhiko.

In: International Journal of Computer Applications in Technology, Vol. 35, No. 2-4, 06.2009, p. 204-209.

Research output: Contribution to journalArticle

@article{ee1a1b2548dd4b6c979a968d3fbc50b6,
title = "Analysis of the effect of headline news in financial market through text categorisation",
abstract = "In this paper, we analyse the relation between stock-price returns and Headline News. Headline News is a very important source of information in asset management and is sent in large quantities every day. We study the effect of more than 13,000 Headline News sent from Jiji Press. We classify Headline News into three types using text categorisation and analyse the reaction of a stock-price return to each types of news. From our research, we figure out following issues: (1) we make the text categorisation system that has about 80{\%} of classification accuracy, (2) this system can extract effective information to stock-price returns from Headline News and (3) such information is more effective to the small firms.",
keywords = "Headline news, Na{\"i}ve bayes, Text auto categorisation, Text mining",
author = "Satoru Takahashi and Hiroshi Takahashi and Kazuhiko Tsuda",
year = "2009",
month = "6",
doi = "10.1504/IJCAT.2009.026597",
language = "English",
volume = "35",
pages = "204--209",
journal = "International Journal of Computer Applications in Technology",
issn = "0952-8091",
publisher = "Inderscience Enterprises Ltd",
number = "2-4",

}

TY - JOUR

T1 - Analysis of the effect of headline news in financial market through text categorisation

AU - Takahashi, Satoru

AU - Takahashi, Hiroshi

AU - Tsuda, Kazuhiko

PY - 2009/6

Y1 - 2009/6

N2 - In this paper, we analyse the relation between stock-price returns and Headline News. Headline News is a very important source of information in asset management and is sent in large quantities every day. We study the effect of more than 13,000 Headline News sent from Jiji Press. We classify Headline News into three types using text categorisation and analyse the reaction of a stock-price return to each types of news. From our research, we figure out following issues: (1) we make the text categorisation system that has about 80% of classification accuracy, (2) this system can extract effective information to stock-price returns from Headline News and (3) such information is more effective to the small firms.

AB - In this paper, we analyse the relation between stock-price returns and Headline News. Headline News is a very important source of information in asset management and is sent in large quantities every day. We study the effect of more than 13,000 Headline News sent from Jiji Press. We classify Headline News into three types using text categorisation and analyse the reaction of a stock-price return to each types of news. From our research, we figure out following issues: (1) we make the text categorisation system that has about 80% of classification accuracy, (2) this system can extract effective information to stock-price returns from Headline News and (3) such information is more effective to the small firms.

KW - Headline news

KW - Naïve bayes

KW - Text auto categorisation

KW - Text mining

UR - http://www.scopus.com/inward/record.url?scp=67650333260&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=67650333260&partnerID=8YFLogxK

U2 - 10.1504/IJCAT.2009.026597

DO - 10.1504/IJCAT.2009.026597

M3 - Article

VL - 35

SP - 204

EP - 209

JO - International Journal of Computer Applications in Technology

JF - International Journal of Computer Applications in Technology

SN - 0952-8091

IS - 2-4

ER -