Quantifying Market Sentiment for the Empirical Analysis in the Japanese Stock Market

カブシキ　シジョウ　ヲ　ハンエイスル　センチメイト　インデックス　ノ　コウチク　ト　カブカ　セツメイリョク　ノ　ジッショウ　ブンセキ

カズミ, タクロウ

Kazumi, Takuro

The Economic Society of Osaka University　and　Graduate School of Economics, Osaka University

オオサカ　ダイガク　ケイザイ　ガッカイ オオサカ　ダイガク　ダインガクイン　ケイザイガク　ケンキュウカ

日本経済新聞

テキスト・マイニング

株価予測可能性

Analysis

Nikkei

Text Mining

Predictability of Stock Price

The purpose of this paper is to quantify the market sentiment as two indexes and examine whether they can help predict stock prices in the Japanese market. Sentiment analysis is gaining increasing interest in both academia and business. Along these lines, Ishijima et al. (2014) created a sentiment index that quantifies the positive or negative emotion that might appear in entire articles of Nikkei which is the most popular business newspaper in Japan. They concluded that the sentiment index significantly predicts stock prices three days in advance. We re-examine their results by suggesting a new sentiment index quantified from the articles limited to the economic-activity-related news and explore the implication on how the sentiment index can help explain Japanese stock price. Our findings are three-fold: (i) Sentiment index created from the articles limited to the economic-activity-related news significantly allows us to explain Nikkei 225 and the market trading volume of the next business day. (ii) We cannot observe the return reversal referred in the literature. (iii) SI will follow the stock price.