2016 Fiscal Year Final Research Report
Infrastructure for real-time information extraction from large-scale graph streams
Project/Area Number |
26280112
|
Research Category |
Grant-in-Aid for Scientific Research (B)
|
Allocation Type | Partial Multi-year Fund |
Section | 一般 |
Research Field |
Web informatics, Service informatics
|
Research Institution | Kyoto University |
Principal Investigator |
Tajima Keishi 京都大学, 情報学研究科, 教授 (60283876)
|
Co-Investigator(Kenkyū-buntansha) |
櫻井 保志 熊本大学, 自然科学研究科, 教授 (30466411)
|
Project Period (FY) |
2014-04-01 – 2017-03-31
|
Keywords | Webマイニング / グラフマイニング / ソーシャルネットワーク / 時間発展グラフ / モデル化 / 予測技術 |
Outline of Final Research Achievements |
The goal of this project is to establish the infrastructure for real-time analysis of temporal evolution of graph-structured data, such as the change of user activities on the Internet along the time, the temporal change of information flow on social networks, and the temporal change of traffic flow on transportation networks. To achieve this goal, we developed several methods for highly-efficient and accurate modelling of temporal evolution of these kinds of data, and also several methods for prediction of their future changes based on these modelling methods. For example, we developed a method of modelling and predicting the temporal change of frequencies of appearances of some words that are conflicting with each other, and a method of predicting structural changes of social networks that will happen after appearances of some new nodes.
|
Free Research Field |
計算機科学
|