利用關聯規則發掘書籍最適性借閱之推薦策略

Using Association Rules to Find the Most Adaptive Borrowing Strategies of Book Recommendations

本論文以讀者之借閱資料為探勘的資料來源，每一筆借閱資料包含有讀者曾經借閱過的書籍項目，利用關聯規則 (association rules) 從以下兩方面來發掘書籍最適性借閱的推薦策略：一是以某一請者為探勘的目標，文中提出一個探勘關聯規則的演算法，其關聯規則的前置項目組，必須包含於此一請者的借閱資料中，根據關聯規則所顯示出的傾向特徵，可發掘此一請者最適性借閱的書籍推薦；二是以某一書籍為探勘的目標，文中提出一個探勘關聯規則的演算法，其關聯規則的後置項目組必須為此一書籍，根據關聯規則所顯示出的特徵，可發掘此一書籍最適性借閱的讀者。根據文中所提出的方法，設計與建置一個發掘書籍最適性借閱的推薦系統。此探勘結果，對圖書館在規畫適性化的書籍推薦服務時，可以提供非常有用的參考資訊。

In this paper, we use readers' borrowing history records as the source data of mining. Each borrowing history record contains a reader ever borrowed books, and use association rules to find the most adaptive borrowing strategies of book recommendations from two aspects. One is to let one reader as the target of mining and propose an algorithm to mine association rules whose antecedents are contained in the reader's borrowing history record. According to the characteristics of the association rules, we can find the most adaptive borrowing of book recommendations for the reader. The other is to let one book as the target of mining and propose an algorithm to mine association rules whose consequents are the book. According to the characteristics of the association rules, we can find the most adaptive readers of borrowing the book. We design and construct a mining system for finding the most adaptive borrowing of book recommendations according to we propose the both methods. The results of the mining can provide very useful information to plan the services of adaptive book recommendations for libraries.