基于改进K-Means算法的图书馆读者阅读需求实证研究  

An Empirical Study of Library Readers’Reading Needs Based on Improved K-Means Algorithm

作　　者：孙卫忠 张楠[2] 李亚函[2] 高迎平[2] Sun Weizhong;Zhang Nan;Li Yahan;Gao Yingping

机构地区：[1]河北工业大学图书馆,天津300401 [2]河北工业大学,天津300401

出　　处：《新世纪图书馆》2020年第5期59-64,89,共7页New Century Library

基　　金：河北省社会科学基金项目“面向用户科研需求的高校图书馆信息服务体系研究”(项目编号:HB17TQ009)研究成果之一。

摘　　要：论文对图书馆读者的需求偏好进行数据挖掘,能够为图书馆开展个性化主动服务提供有效参考。由于传统K-Means算法存在对初始中心敏感的问题,文章从数据内部分布特征出发,提出改进K-Means的算法,对图书馆读者阅读需求进行了实证研究。结果显示,读者的阅读需求存在差异性,从而针对读者阅读需求提出提升高校图书馆个性化服务的对策建议。Data mining of library readers’demand preferences can provide an effective reference for libraries to carry out personalized and active services and rationally allocate collection resources.Because the traditional K-Means algorithm is sensitive to the initial center,this paper proposes an improved K-Means algorithm based on the internal distribution of data,and makes an empirical study on the reading needs of library readers.The results show that there are differences in the reading needs of readers,so the countermeasures and suggestions to improve the personalized service of university library are put forward.

关 键 词：图书馆 读者阅读需求 改进K-MEANS算法 实证研究 

分 类 号：G252[文化科学—图书馆学]