| Presentation | 2006-07-14 A Clustering Method Based on the Temporal Relation of Query Keywords for Web Search Tomoyo KAGE, Kazutoshi SUMIYA, |
|---|---|
| PDF Download Page |  PDF download Page Link |
| Abstract(in Japanese) | (See Japanese page) |
| Abstract(in English) | The Web search engines based on the keywords are popular because it is easy for users to retrieve information. However, retrieved Web pages have various contents and perspectives, and the pages do not match users' intentions because level of importance is high. For the reasons stated above, some clustering methods of topic or relationship are proposed. The clustering methods are divided into methods based on contents and methods based on structure. However, same topic' s or related pages may be mixed-up some perspectives about query keywords. It is difficult for the conventional methods analyzing only today to analyze the perspectives about query keywords, and the methods can not solve the problem. In this study, we propose new clustering method based on a temporal aspect. We classify retrieved pages into same perspectives groups about query keywords by Web logs. First, we extract URLs included query keywords and analyze appearance tendencies of the keywords' each URL. Next, we retrieve Web pages based on the temporal relations of query keywords. Retrieved Web pages are clustered based on the temporal relations. In this paper, we describe our proposed method and examine the evaluation and the analysis. |
| Keyword(in Japanese) | (See Japanese page) |
| Keyword(in English) | Information Retrieval / Web Archive / Clustering |
| Paper # | DE2006-118 |
| Date of Issue |
| Conference Information | |
| Committee | DE |
|---|---|
| Conference Date | 2006/7/7(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 Clustering Method Based on the Temporal Relation of Query Keywords for Web Search |
| Sub Title (in English) | |
| Keyword(1) | Information Retrieval |
| Keyword(2) | Web Archive |
| Keyword(3) | Clustering |
| 1st Author's Name | Tomoyo KAGE |
| 1st Author's Affiliation | Graduate School of Human Science and Environment, University of Hyogo() |
| 2nd Author's Name | Kazutoshi SUMIYA |
| 2nd Author's Affiliation | School of Human Science and Environment, University of Hyogo |
| Date | 2006-07-14 |
| Paper # | DE2006-118 |
| Volume (vol) | vol.106 |
| Number (no) | 150 |
| Page | pp.pp.- |
| #Pages | 6 |
| Date of Issue | |