图书情报工作

图书情报工作 >

2015 , Vol. 59 >Issue 11: 143 - 148

DOI: https://doi.org/10.13266/j.issn.0252-3116.2015.11.020

知识组织

基于机器学习的高校图书馆用户偏好检索系统研究

  • 沈敏 ,
  • 杨新涯 ,
  • 王楷
展开
  • 1. 重庆大学图书馆, 重庆, 400044;
    2. 重庆大学自动化学院, 重庆, 400044
沈敏(ORCID:0000-0001-5650-5428),馆员,硕士,E-mail:smin@cqu.edu.cn;杨新涯(ORCID:0000-0002-5267-4993),研究馆员,博士;王楷(ORCID:0000-0002-0788-561X),讲师,博士。

收稿日期: 2015-05-06

  修回日期: 2015-05-19

  网络出版日期: 2015-06-05

基金资助

本文系国家社会科学基金项目“智慧图书馆理论与系统实践研究”(项目编号:13XTQ009)研究成果之一。

收起

Research on User Preference Retrieval System of University Library Based on Machine Learning

  • Shen Min ,
  • Yang Xinya ,
  • Wang Kai
Expand
  • 1. Chongqing University Library, Chongqing 400044;
    2. School of Automation, Chongqing University, Chongqing 400044

Received date: 2015-05-06

  Revised date: 2015-05-19

  Online published: 2015-06-05

Fold

摘要

[目的/意义] 针对大数据环境下高校图书馆检索系统的信息超载问题, 提出一种机器学习方法, 为用户提供个性化的偏好检索服务。[方法/过程] 通过提取用户检索行为大数据中的用户特征, 利用监督机器学习方法, 在线学习可随用户偏好同步变化的自适应检索模型, 预测用户对文献的选择概率, 优化检索结果的排序。[结果/结论] 设计出用户偏好检索原型系统, 介绍用户偏好检索系统工作流程, 对比分析系统效果, 并对系统进行客观评价。

关键词： 机器学习; 高校图书馆; 用户偏好; 偏好检索

本文引用格式

沈敏 , 杨新涯 , 王楷 . 基于机器学习的高校图书馆用户偏好检索系统研究[J]. 图书情报工作, 2015 , 59(11) : 143 -148 . DOI: 10.13266/j.issn.0252-3116.2015.11.020

Abstract

[Purpose/significance] For the information overload problem of traditional retrieval system in university library under big data environment, an online learning method is proposed to provide users personalized preference retrieval services. [Method/process] By extracting users' characteristics from big data of their retrieval behaviors, and the supervising machine learning method, this paper learns an adaptive retrieval model which can synchronize changes with the users' preference online, predicts users' selection probability for the literature and optimizes the sorting order of the retrieval results. [Result/conclusion] This paper designs a user preference retrieval prototype system, introduces the workflow of user preference retrieval system, makes a comparative analysis on the effectiveness, and objectively evaluates the system.

Key words： machine learning; university library; user preference; preference retrieval

参考文献

[1] 栾旭伦. 大数据环境下高校图书馆个性化信息服务系统研究[J]. 图书馆学刊, 2014(8): 118-121.
[2] 官思发, 朝乐门. 大数据时代信息分析的关键问题、挑战与对策[J]. 图书情报工作, 2015, 59(3): 12-18.
[3] 来红梅. 大数据时代图书馆信息服务面临的挑战与对策[J]. 图书馆学刊, 2014(3): 91-93.
[4] Tan J S F, Lu E H C, Tseng V S, et al. Preference-oriented mining techniques for location-based store search [J]. Knowledge and Information Systems, 2013, 34(1): 147-169.
[5] 何军, 刘业政. 基于社交关系和影响力的在线社交网络用户兴趣偏好获取方法研究[J]. 情报学报, 2014, 33(7): 730-739.
[6] 史艳翠,孟祥武,张玉洁,等. 一种上下文移动用户偏好自适应学习方法[J]. 软件学报,2012(10):2533-2549.
[7] Bian Jiang, Long Bo, Li Lihong, et al. Exploiting user preference for online learning in Web content optimization systems[EB/OL].[2015-04-18]. http://dl.acm.org/citation.cfm?id=2493259.
[8] 桑艳艳, 刘培刚, 李勇. 拟合用户偏好的个性化搜索[J]. 情报科学, 2008(8):1248-1251.
[9] Leung K W T, Lee D L, Ng W, et al. A framework for personalizing Web search with concept-based user profiles[EB/OL].[2015-04-18]. http://www.cs.ust.hk/~wilfred/paper/toit12.pdf.
[10] Mandl T, Womser H C. A framework for long-term learning of topical user preferences in information retrieval[J]. New Library World, 2004, 105: 184-195.
[11] 蔡淑琴,胡慕海,叶波,等.情境化推荐中基于超图模式的用户偏好漂移识别研究[J].情报学报,2011,30(8):802-811.
[12] Marin L, Isern D, Moreno A, et al. On-line dynamic adaptation of fuzzy preferences [J]. Information Sciences, 2013, 220(20): 5-21.
[13] 胡雨成, 于俊清, 黄贤强,等. 足球视频搜索引擎中的用户偏好挖掘[J]. 中国图象图形学报, 2014, 19(4): 622-629.
[14] 陆伟, 张晓娟. 基于主题与用户偏好分析的查询推荐研究[J]. 情报学报, 2012, 31(12): 1252-1258.
[15] Agosti M, Crivellari F, Nunzio G M D, et al. Understanding user requirements and preferences for a digital library Web portal [J]. International Journal on Digital Libraries, 2010, 11(4): 225-238.
[16] Mark A P. Student preferences in library website vocabulary[J]. Library Philosophy and Practice, 2011(6):1-17.
[17] Carlos A F, Roberto W, Renato F. Custom ordering on digital library information retrieval[EB/OL].[2015-04-18]. http://dl.acm.org/citation.cfm?id=1858505.
[18] Bernadetta M, Ngoc T N. Tuning user profiles based on analyzing dynamic preference in document retrieval systems[J]. Multimedia Tools and Applications, 2013, 65(1): 93-118.
[19] Claus D, Johann E. Efficient top-k retrieval for user preference queries[C]//SAC. Proceedings of the 2011 ACM Symposium on applied computing. Taiwan:ACM. 2011: 1045-1052.
[20] Li Ming, Li Hang, Zhou Zhihua. Semi-supervised document retrieval[J]. Information Processing and Management, 2009, 45(3): 341-355.
[21] Sun Yang, Li Huajing, Councill I G, et al. Measuring user preference changes in digital libraries[C]//CIKM. Proceeding of the 17th ACM Conference on Information and Knowledge Management. California:ACM, 2008: 1497-1498.

Options
文章导航

/

〈 〉