Presentation 2004/7/7
A Topic Structute Graph Approach for Discovering Topic Changes of News Articles
Hidetoshi HAYASHI, Taro TEZUKA, Satoshi OYAMA, Katsumi TANAKA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In order to extract topic changes of news themes from a set of news articles, relationships between articles are analyzed from both quantitative and qualitative aspects, based on Topic Structure Graph. First, the quantitative analysis proves that similarity calculation at the level of Topic Structure Graph can express the strength of relationships between the articles more precisely than similarity calculation at the level of keywords. Second, the qualitative analysis categorizes the common keywords between the articles based on node degree and gives the sense of relations between the articles. Finally, based on these results, we proposed a method of extracting word-centric topic changes of news themes.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Topic Structure Graph / Data Mining / Time-series Data
Paper # DE2004-50
Date of Issue

Conference Information
Committee DE
Conference Date 2004/7/7(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Data Engineering (DE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A Topic Structute Graph Approach for Discovering Topic Changes of News Articles
Sub Title (in English)
Keyword(1) Topic Structure Graph
Keyword(2) Data Mining
Keyword(3) Time-series Data
1st Author's Name Hidetoshi HAYASHI
1st Author's Affiliation Department of Social Infomatics, Kyoto University()
2nd Author's Name Taro TEZUKA
2nd Author's Affiliation Department of Social Infomatics, Kyoto University
3rd Author's Name Satoshi OYAMA
3rd Author's Affiliation Department of Social Infomatics, Kyoto University
4th Author's Name Katsumi TANAKA
4th Author's Affiliation Department of Social Infomatics, Kyoto University
Date 2004/7/7
Paper # DE2004-50
Volume (vol) vol.104
Number (no) 177
Page pp.pp.-
#Pages 6
Date of Issue