Integrating multiple internet directories by instance-based learning

Ryutaro Ichise, Hiedeaki Takeda, Shinichi Honiden

研究成果: Conference article

36 引用 (Scopus)

抄録

Finding desired information on the Internet is becoming increasingly difficult. Internet directories such as Yahoo!, which organize web pages into hierarchical categories, provide one solution to this problem; however, such directories are of limited use because some bias is applied both in the collection and categorization of pages. We propose a method for integrating multiple Internet directories by instance-based learning. Our method provides the mapping of categories in order to transfer documents from one directory to another, instead of simply merging two directories into one. We present herein an effective algorithm for determining similar categories between two directories via a statistical method called the k-statistic. In order to evaluate the proposed method, we conducted experiments using two actual Internet directories, Yahoo! and Google. The results show that the proposed method achieves extensive improvements relative to both the Naive Bayes and Enhanced Naive Bayes approaches, without any text analysis on documents.

元の言語English
ページ(範囲)22-28
ページ数7
ジャーナルIJCAI International Joint Conference on Artificial Intelligence
出版物ステータスPublished - 2003 12 1
外部発表Yes
イベント18th International Joint Conference on Artificial Intelligence, IJCAI 2003 - Acapulco, Mexico
継続期間: 2003 8 92003 8 15

Fingerprint

Internet
Merging
Websites
Statistical methods
Statistics
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

これを引用

@article{4468849d2c43477c80b0c0f27cae52b1,
title = "Integrating multiple internet directories by instance-based learning",
abstract = "Finding desired information on the Internet is becoming increasingly difficult. Internet directories such as Yahoo!, which organize web pages into hierarchical categories, provide one solution to this problem; however, such directories are of limited use because some bias is applied both in the collection and categorization of pages. We propose a method for integrating multiple Internet directories by instance-based learning. Our method provides the mapping of categories in order to transfer documents from one directory to another, instead of simply merging two directories into one. We present herein an effective algorithm for determining similar categories between two directories via a statistical method called the k-statistic. In order to evaluate the proposed method, we conducted experiments using two actual Internet directories, Yahoo! and Google. The results show that the proposed method achieves extensive improvements relative to both the Naive Bayes and Enhanced Naive Bayes approaches, without any text analysis on documents.",
author = "Ryutaro Ichise and Hiedeaki Takeda and Shinichi Honiden",
year = "2003",
month = "12",
day = "1",
language = "English",
pages = "22--28",
journal = "IJCAI International Joint Conference on Artificial Intelligence",
issn = "1045-0823",

}

TY - JOUR

T1 - Integrating multiple internet directories by instance-based learning

AU - Ichise, Ryutaro

AU - Takeda, Hiedeaki

AU - Honiden, Shinichi

PY - 2003/12/1

Y1 - 2003/12/1

N2 - Finding desired information on the Internet is becoming increasingly difficult. Internet directories such as Yahoo!, which organize web pages into hierarchical categories, provide one solution to this problem; however, such directories are of limited use because some bias is applied both in the collection and categorization of pages. We propose a method for integrating multiple Internet directories by instance-based learning. Our method provides the mapping of categories in order to transfer documents from one directory to another, instead of simply merging two directories into one. We present herein an effective algorithm for determining similar categories between two directories via a statistical method called the k-statistic. In order to evaluate the proposed method, we conducted experiments using two actual Internet directories, Yahoo! and Google. The results show that the proposed method achieves extensive improvements relative to both the Naive Bayes and Enhanced Naive Bayes approaches, without any text analysis on documents.

AB - Finding desired information on the Internet is becoming increasingly difficult. Internet directories such as Yahoo!, which organize web pages into hierarchical categories, provide one solution to this problem; however, such directories are of limited use because some bias is applied both in the collection and categorization of pages. We propose a method for integrating multiple Internet directories by instance-based learning. Our method provides the mapping of categories in order to transfer documents from one directory to another, instead of simply merging two directories into one. We present herein an effective algorithm for determining similar categories between two directories via a statistical method called the k-statistic. In order to evaluate the proposed method, we conducted experiments using two actual Internet directories, Yahoo! and Google. The results show that the proposed method achieves extensive improvements relative to both the Naive Bayes and Enhanced Naive Bayes approaches, without any text analysis on documents.

UR - http://www.scopus.com/inward/record.url?scp=84880768438&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880768438&partnerID=8YFLogxK

M3 - Conference article

SP - 22

EP - 28

JO - IJCAI International Joint Conference on Artificial Intelligence

JF - IJCAI International Joint Conference on Artificial Intelligence

SN - 1045-0823

ER -