2011 Fiscal Year Final Research Report
Extraction and reorganization of topic transition patterns in recorded document
| Project/Area Number |
20700129
|
|---|
| Research Category |
Grant-in-Aid for Young Scientists (B)
|
| Allocation Type | Single-year Grants |
|---|
| Research Field |
Intelligent informatics
|
|---|
| Research Institution | Hitotsubashi University (2010-2011)
The University of Tokyo (2008-2009) |
|---|
Principal Investigator |
|
|---|
| Project Period (FY) |
2008 – 2011
|
| Keywords | 情報システム / 人工知能 / 可視化 / 設計工学 |
|---|
| Research Abstract |
This research proposed a system which focused chronological order of documents had accumulated over a period of time. It extracted and reorganized topics and its transitions from documents to acquire knowledge. It decomposed each document into smaller text fragments and grouped them into clusters of fragments. We regarded a cluster of text fragments as a topic. The system made document groups based on elapsed time, and calculated relevance of topics in neighboring document groups. Then it obtained topics and their transition. It could sort out topics temporal topics and constant topics. It also reorganized topics and their transition with keywords indicated by a user.
|
