人工知能学会論文誌
Online ISSN : 1346-8030
Print ISSN : 1346-0714
検索
OR
閲覧
検索
20 巻 , 5 号
選択された号の論文の4件中1~4を表示しています
    • |<
    • <
    • 1
    • >
    • >|
論文
  • 烏 云, 狩野 均
    20 巻 (2005) 5 号 p. 318-325
    公開日: 2005/07/05
    ジャーナル フリー
    Socioeconomic phenomena, cultural progress and political organization have recently been studied by creating artificial societies consisting of simulated agents. In this paper we propose a new method to design action rules of agents in artificial society that can realize given requests using genetic algorithms (GAs).
    In this paper we propose an efficient method for designing the action rules of agents that will constitute an artificial society that meets a specified demand by using a GAs. In the proposed method, each chromosome in the GA population represents a candidate set of action rules and the number of rule iterations. While a conventional method applies distinct rules in order of precedence, the present method applies a set of rules repeatedly for a certain period. The present method is aiming at both firm evolution of agent population and continuous action by that. Experimental results using the artificial society proved that the present method can generate artificial society which fills a demand in high probability.
    抄録全体を表示
  • 川島 貴広, 石川 勉
    20 巻 (2005) 5 号 p. 326-336
    公開日: 2005/07/05
    ジャーナル フリー
    We have developed a knowledge base of words as a tool to measure the semantic similarity between words. In this paper, we evaluate the knowledge base of words comparing with thesauruses, which are commonly used for measuring similarity. Thesauruses of NIHONGO-GOI-TAIKEI(NGT) and Japan Electronic Dictionary(EDR) are selected for the evaluation. For similarity calculation methods using thesauruses, we adopt a newly proposed method, in which each word is represented with vector using the structural feature of thesauruses and the degree of similarity between words is calculated by the inner product of their vectors, in addition to traditional methods based on the path length between categories or the depth of the subsumer. Evaluation is carried out through the two methods, that is, a traditional method based on human rating and the method we have already proposed, feasible for evaluating automatically without human judgment. Evaluation result shows that the knowledge base of word is superior to the both thesauruses(NGT outperforming EDR) as measurement tools, and the proposed calculation method outperforms the traditional ones. The result also shows that our evaluation method is a practical one, by investigating the correlation of both methods.
    抄録全体を表示
  • 森 純一郎, 松尾 豊, 石塚 満
    20 巻 (2005) 5 号 p. 337-345
    公開日: 2005/08/02
    ジャーナル フリー
    With the currently growing interest in the Semantic Web, personal metadata to model a user and the relationship between users is coming to play an important role in the Web. This paper proposes a novel keyword extraction method to extract personal information from the Web. The proposed method uses the Web as a large corpus to obtain co-occurrence information of words. Using the co-occurrence information, our method extracts relevant keywords depending on the context of a person. Our evaluation shows better performance to other keyword extraction methods. We give a discussion about our method in terms of general keyword extraction for the Web.
    抄録全体を表示
  • 村上 知子, 吉岡 信和, 折原 良平, 古川 康一
    20 巻 (2005) 5 号 p. 346-355
    公開日: 2005/08/02
    ジャーナル フリー
    Product recommendation system is realized by applying business rules acquired by data maining techniques. Business rules such as demographical patterns of purchase, are able to cover the groups of users that have a tendency to purchase products, but it is difficult to recommend products adaptive to various personal preferences only by utilizing them. In addition to that, it is very costly to gather the large volume of high quality survey data, which is necessary for good recommendation based on personal preference model. A method collecting kansei information automatically without questionnaire survey is required. The constructing personal preference model from less favor data is also necessary, since it is costly for the user to input favor data.
    In this paper, we propose product recommendation system based on kansei information extracted by text mining and user's preference model constructed by Category-guided Adaptive Modeling, CAM for short. CAM is a feature construction method that can generate new features constructing the space where same labeled examples are close and different labeled examples are far away from some labeled examples.
    It is possible to construct personal preference model by CAM despite less information of likes and dislikes categories. In the system, retrieval agent gathers the products' specification and user agent manages preference model, user's likes and dislikes. Kansei information of the products is gained by applying text mining technique to the reputation documents about the products on the web site. We carry out some experimental studies to make sure that prefrence model obtained by our method performs effectively.
    抄録全体を表示
    • |<
    • <
    • 1
    • >
    • >|
feedback
Top