電気学会論文誌C(電子・情報・システム部門誌)
Online ISSN : 1348-8155
Print ISSN : 0385-4221
ISSN-L : 0385-4221
<ソフトウェア・情報処理>
Kullback Leibler Divergenceに基づいた遺伝的アルゴリズムによるユーザプロファイル作成
柳本 豪一大松 繁
著者情報
ジャーナル フリー

2006 年 126 巻 3 号 p. 389-394

詳細
抄録

In this paper we propose a user profile creation method using the Kullback Leibler divergence. To cope with information flood, many information filtering systems have been developed up to now. In the information filtering systems it is important to create a user profile which represents user's interests correctly. Since almost all information filtering systems are developed with techniques of information retrieval, machine learning, and pattern recognition, they often use a linear function as a discriminant function. To classify information in the field of document classification more precisely, the systems have been reported which use a non-linear function as a discriminant function. The proposed method is to use the Kullback Leibler divergence as a discriminant function which denotes to user's interest in the information filtering system. To identify an optimal discriminat function with documents which a user evaluates, we use the real-coded genetic algorithm. We compare the present method with the other one using a linear discriminant function and confirm the effectiveness of the proposing method.

著者関連情報
© 電気学会 2006
前の記事 次の記事
feedback
Top