Implementation of Discovered-Rule-Filtering System(Artificial Intelligence II)

概要

論文の詳細を見る
Data mining systems semi-automatically discover knowledge by examining large volumes of data, but the knowledge discovered is not always novel to users. We proposed a discovered-rule-filtering approach that uses information retrieval results from the Internet to assess rules discovered by data mining and find those that are novel to the user. To realize this approach, we developed 2 methods: the micro view method and the macro view method. In the micro view method, we extract keywords from each discovered rule and rank the rule referring to the number of hits returned when the keywords are submitted to an appropriate database. In the macro view method, we refer to the number of hits by submitting every pair of extracted keywords and form keyword clusters according to the results. We developed a discovered-rule-filtering system called DRFS which employs the two methods. DRFS can rank discovered. rules in the field of medical domain according the results of information retrieval from the MEDLINE database.
一般社団法人情報処理学会の論文
2004-12-04