利用關聯規則發掘圖書館個人化之書籍推薦

Using Association Rules to Find Personalized Book Recommendation for Library

陳垂呈(Chui-Cheng Chen)

《圖書資訊學刊》 2卷2期 (2004/09) Pp. 87-103

https://doi.org/10.6182/jlis.2004.2(2).087

摘要

在本篇論文中，我們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與其興趣度，並以某一讀者為探勘的目標，利用關聯規則(association rules)分別從下兩方面來發掘讀者個人化的書籍推薦：首先，我們只考量書籍是否出現在借閱資料中，設計一個探勘關聯規則的方法，且探勘出之關聯規則的前置項目組，必須被包含於此一讀者的借閱資料中，根據關聯規則所顯示出的特徵，我們可發掘此一讀者適性化的書籍推薦。再者，我們考量在借閱資料中包含有讀者對曾經借閱過之書籍的興趣度，設計一個探勘包含有興趣度之關聯規則的方法，且探勘出包含有興趣度之關聯規則的前置項目組，必須被包含於此一讀者的借閱資料中，根據包含有興趣度之關聯規則所顯示出的特徵，我們可發掘包含有興趣度之此一讀者適性化的書籍推薦。此探勘結果，對於圖書館在發掘個人化的書籍推薦時，可以提供非常有用的參考資訊。

關鍵字

資料探勘 ； 關聯規則 ； 借閱資料 ； 書籍推薦

並列摘要

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 the reader's the degrees of interest for those books. We let one reader as the target of mining, and use association rules to find the personalized book recommendations for the reader from two aspects, respectively. First, we only consider the books whether they are contained in borrowing history records or not, and propose a method 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 adaptive book recommendations for the reader. Moreover, we consider the books with readers' interests in the borrowing history records, and propose another method to mine association rules with interesting degrees whose antecedents are contained in the reader's borrowing history record. According to the characteristics of the association rules with interesting degrees, we can find the reader's the adaptive book recommendations for considering his interests. The results of the mining can provide very useful information to find personalized book recommendation for library.

並列關鍵字

data mining ； association rules ； borrowing history records ； book recommendations

參考文獻

Agrawal, R.,Imieliski, T.,Swami, A.(1993).Proceedings of the 1993 ACM SIGMOD Cnference.

Agrawal, R.,Srikant, R.(1994).Proceedings of the 20th International Conference on Very Large Data Bases, Santiago.

Agrawal, R.,Srikant, R.(1995).Proceedings of the 20th International Conference on Very Large Data Bases, Santiago.

Agrawal, R.,Srikant, R.(1996).Proceedings of the ACM SIGMOD Conference on Management of Data.

Chen, M. S.,Park, J. S.(1997).Using a Hash-Based Method with Transaction Trimming for Mining Association Rules.IEEE Transactions on Knowledge and Data Engineering.9(5)