著者

泉 晃

雑誌

経営課題にAIを! ビジネス・インフォマティクス研究会資料 = SIG-BI

巻号頁・発行日

vol.1, no.4, 2014-11-20

---

Overview about current status of personal data and the various methods of privacy- preserving data mining which is a technique for the privacy protection.Then,discuss methods and collateral criteria that must be in terms of the use of personal data, as a study design. Specifi- cally, applying the existing methods such as k-anonymity to the actual personal data and extracts problems. If necessary, propose a new method for solving problems.

著者

五島 圭一 高橋 大志 寺野 隆雄

雑誌

経営課題にAIを! ビジネス・インフォマティクス研究会資料 = SIG-BI

巻号頁・発行日

vol.1, no.1, 2014-11-20

---

Many stuides have been attempting to uncover the relationship between asset price fluctuations and textual information. However, in many cases, subjective evaluations of researchers have significant impacts on results. In this paper, we propose an objective evaluation method of news article using stock prices. Firstly, we give class labels (negative-positive) to every news articles by using event study analysis. Secondly, we compute vector representations of news aritcles by morphological analysis and tf-idf. Finally, we make Support Vector Machine classifier and give class labels (negative-positive) to other news articles. This method enable objective analyses of textual data in financial contexts.