Authors: Yasuo Yamashita; Hiroaki Joutaki; Hiroshi Takahashi
Addresses: Quantitative Investment Department, Sumitomo Mitsui Trust Bank, 1-4-1 Marunouchi, Chiyoda-ku, Tokyo 100-8233, Japan ' Fixed Income Investment Department, Sumitomo Mitsui Trust Bank, 1-4-1 Marunouchi, Chiyoda-ku, Tokyo 100-8233, Japan ' Graduate School of Business Administration, Keio University, 2-15-45 Mita, Minato-Ku, Tokyo 108-8345, Japan
Abstract: This research analysed the relationship between headlines in the news and the stock market in Japan through text mining technology. As a result of intensive analyses, we found a significant relationship between the stock index return changes and the negative (or positive) news classified by keywords. At the same time, we also found that the measure of constructing a keyword list has a significant impact on the performance of this classification.
Keywords: text mining; stock markets; finance; asset management; asset pricing; headline news; Japan; market influences.
International Journal of Intelligent Systems Technologies and Applications, 2013 Vol.12 No.3/4, pp.328 - 342
Received: 05 Nov 2012
Accepted: 11 Jun 2013
Published online: 25 Sep 2013 *