Title: Analysis of the effect of Headline News in financial market through text categorisation

Authors: Satoru Takahashi, Hiroshi Takahashi, Kazuhiko Tsuda

Addresses: Quantitative Investment Department, Chuo Mitsui Trust and Banking Company Ltd., 3-23-1, Shiba, Minato-ku, Tokyo 105-8574, Japan. ' Graduate School of Humanities and Social Sciences, Okayama University, 1-1, Tsushima-Naka, 1-Chome, Okayama, Japan. ' Graduate School of Systems Management, University of Tsukuba, 3-29-1 Otsuka, Bunkyo-ku, Tokyo, Japan

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: text mining; text auto categorisation; naive Bayes; Headline News; stock price returns; asset management; text categorisation; classification accuracy; small firms; financial markets.

DOI: 10.1504/IJCAT.2009.026597

International Journal of Computer Applications in Technology, 2009 Vol.35 No.2/3/4, pp.204 - 209

Published online: 20 Jun 2009 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article