SEKI, KazuhiroAs of Apr 2022
Professor, Konan University
Text analytics, Data science, Machine learning, and their application to real-world problems to develop intelligent information processing/management systems.
- Ph.D. in Information Science (Indiana University, Bloomington)
- Professor, Konan University, 2021-Present
- Associate Professor, Konan University, 2014-2021
Books and Chapters
- “Measuring Social Change Using Text Data: A Simple Distributional Approach.”
- Reconstruction of the Public Sphere in the Socially Mediated Age. Springer, pp. 139-164, November 2017. (with Takashi Kamihigashi and Masahiko Shibamoto.)
- “Statistical Anaphora Resolution for Japanese Zero Pronouns. ”
- Readings in Japanese Natural Language Processing. CSLI Publications, pp. 108-128, June 2016. (with Atsushi Fujii and Tetsuya Ishikawa.)
Journal Articles and Papers
- “News-based Business Sentiment and its Properties as an Economic Index. ”
- Information Processing & Management (IP&M), Vol. 59, No. 2, 102795, March 2022.
- (with Yusuke Ikuta and Yoichi Matsubayashi)
- “Cross-Lingual Text Similarity Exploiting Neural Machine Translation Models.” Journal of Information Science, Vol. 47, No. 3, pp. 404-418, June 2021.
- “Nowcasting Business Sentiment from Economic News Articles.” IPSJ Journal, Vol. 62, No. 5, pp. 1288-1297, May 2021. (In Japanese)
- (with Yusuke Ikuta)
Academic Association Affiliations
- Information Processing Society of Japan
- The Japanese Society for Artificial Intelligence
Research Projects & Papers
Research Project » 2023FiscalYear » Economic forecast and analysis
Kazuhiro Seki (Senior Researcher, APIR/Professor, Konan University)
With the rapid development of information technology in recent years, large-scale data generated by domestic and international economic activities are becoming available in a variety of forms. The use of data containing extremely rich information, such as text data, is thought to be effective in making more precise judgments and forecasts of macroeconomic conditions. In view of this, this project aims to develop an index using text data, which can be instrumental in discerning economic trends.