首页 | 官方网站   微博 | 高级检索  
     

基于读者借阅二分网络的图书可推荐质量测度方法及个性化图书推荐服务
引用本文:李树青,徐侠,许敏佳.基于读者借阅二分网络的图书可推荐质量测度方法及个性化图书推荐服务[J].中国图书馆学报,2013,39(3):83-95.
作者姓名:李树青  徐侠  许敏佳
作者单位:1. 南京财经大学信息工程学院信息管理与信息系统系
2. 南京人口管理干部学院工商管理系
3. 南京财经大学图书馆技术部
基金项目:本文系国家自然科学基金项目“基于通用加权XML模型的个性化用户兴趣本体研究”(项目编号:71103081)和江苏省高校自然科学研究面上资助项目“通用加权XML模型在便携式个性化用户兴趣本体中的表达方法研究”(项目编号:11KJB630001)的研究成果之一。
摘    要:本文首先提出一种利用读者借阅行为特征来判断图书可推荐质量的思路,并结合读者图书借阅关系所形成的二分网络结构,设计了一种测度图书可推荐质量的迭代算法,从而为个性化图书推荐服务提供了良好的推荐客体.在上述研究的基础上,结合图书类别目录层次、标题语义信息的提取处理方法、基于加权XML模型的用户个性化模式表达方法及其权值扩散策略,提出了三种图书馆个性化图书推荐服务的形式,分别是特定主题的图书推荐服务、现有所借图书的修正型推荐服务和新书推荐服务.最后,文章对相关测试实验及其效果做了必要的说明.

关 键 词:图书借阅网络  二分网络  个性化推荐
收稿时间:2012/11/26 0:00:00
修稿时间:2013/1/23 0:00:00

The Measures of Books' Recommending Quality and Personalized Book Recommendation Service Based on Bipartite Network of Readers and Books' Lending Relationship
Li Shuqing,Xu Xia and Xu Minjia.The Measures of Books'' Recommending Quality and Personalized Book Recommendation Service Based on Bipartite Network of Readers and Books'' Lending Relationship[J].Journal of Library Science In China,2013,39(3):83-95.
Authors:Li Shuqing  Xu Xia and Xu Minjia
Abstract:This paper begins with the introduction of an idea about judging books' recommending quality through the characteristic analysis of the readers' lending behavior. Based on the bipartite network structure of reader and books' lending relationship, an iterative algorithm which can recognize the book's recommending quality is proposed. This algorithm can provide better recommendation objects for personalized book recommendation service. On the basis of the research mentioned-above, combined with the hierarchy of book catalog, the extract of semantic information of titles, the expression of personalized user profile based on weighted XML model and weight's spreading strategy, this paper also discusses three different methods of personalized book recommendation service in library, which include recommendation service of specific topic books, revised recommendation service of borrowed books, new books recommendation service. Finally, this paper reports some related experiments which show the improvement of effect. 9figs. 10tabs. 13refs.
Keywords:Network of book lending    Bipartite network    Personalized recommendation  
本文献已被 万方数据 等数据库收录!
点击此处可从《中国图书馆学报》浏览原始摘要信息
点击此处可从《中国图书馆学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司    京ICP备09084417号-23

京公网安备 11010802026262号