Spatio-temporal text mining based on real-time information retrieval

2015 Fiscal Year Final Research Report

• Project/Area Number: 25330363
• Research Category: Grant-in-Aid for Scientific Research (C)
• Allocation Type: Multi-year Fund
• Section: 一般
• Research Field: Web informatics, Service informatics
• Research Institution: Konan University (2014-2015); Kobe University (2013)
• Principal Investigator: Seki Kazuhiro 甲南大学, 知能情報学部, 准教授 (30444566)
• Project Period (FY): 2013-04-01 – 2016-03-31
• Keywords: リアルタイム検索 / 株価動向予測

Outline of Final Research Achievements

This research project first studied realtime information retrieval systems, which consider temporal properties of users' information needs, as a building block of intelligent information systems, and then investigated spatio-temporal text mining. The main outcome of the project is two-fold: one is to devise a realtime microblog retrieval model modeling trends of topics, and the other is the development of a framework to predict short-term stock price movements using recursive neural networks analyzing breaking news headlines.

Free Research Field

知的情報システム