[目的/意义]调研推荐系统在高校图书馆中的应用现状及存在的问题,为增强图书馆对知识信息的智能处理能力提供参考依据。[方法/过程]通过对国内116所"211工程"院校进行网站访查和问卷调查,用定量分析与定性分析相结合等方法,对调查结果进行归类、分类统计和对比分析。[结果/结论]研究发现,受访高校图书馆均提供非个性化推荐服务,63%受访高校提供个性化推荐服务;推荐服务内容丰富、方式多样、形式各异,79%的高校积极寻求与其他平台的合作,拓宽推荐深度和广度。存在的问题包括:图书馆推荐系统个性化程度不高,过于依赖图书管理集成系统所附带的推荐功能,不够系统化、智慧化;推荐系统满意度有待提高,有相当多的用户担心推荐系统会泄露个人隐私。
[Purpose/significance] Studies on recommender systems in the library field have been mostly focused on theoretical models or technical constructions. They lack data of the current status and real practical issues. This paper aims to investigate the application situation and existing problems of the recommender system in university libraries in order to put forward references for enhancing libraries' knowledge services. [Method/process] Based on website visits and the questionnaire survey of 116 universities included in the "211 Project", data were processed through classified statistics and comparative analysis. [Result/conclusion] The results show that almost all the university libraries offer non-personalized recommender services, and 63% of them provide personalized recommender services. Various recommender systems with diverse services are widely emerging, which reflects great needs for smart knowledge discovery and delivery services. 79% of the university libraries actively seek cooperation with other platforms to broaden their recommending capacities. More personalized recommender systems and systematic and intelligent services are still in demands. In addition, libraries need to pay more attention to readers' satisfaction on the recommender systems, as well as their privacy issues.
[1] PRYOR S.Implementing a 3D printing service in an academic library[J].Journal of library administration,2014,54(1):1-10.
[2] 张文华,胡春,胡光林,等.基于图书馆流通数据的聚类分析研究[J].农业图书情报学刊,2010(10):109-111,130.
[3] 项亮.推荐系统实践[M].北京:人民邮电出版社,2012.
[4] 马文峰,高凤荣,王珊.论数字图书馆个性化信息推荐系统[J].现代图书情报技术,2003(2):16-18.
[5] 孟祥武,纪威宇,张玉洁.大数据环境下的推荐系统[J].北京邮电大学学报,2015(2):1-15.
[6] 朱扬勇,孙婧.推荐系统研究进展[J].计算机科学与探索,2015(5):513-525.
[7] 景民昌.从ACM RecSys'2014国际会议看推荐系统的热点和发展[J].现代情报,2015(4):41-45.
[8] 潘莉,张桁.网络购物推荐系统现状分析[J].电子制作,2014(21):92.
[9] LINDEN G,SMITH B,YORK J.Amazon.com recommendations:item-to-item collaborative filtering[J].IEEE Internet computing,2003,7(1):76-80.
[10] 马文峰.数字图书馆个性化信息服务的探索[J].图书馆杂志,2003(5):30-32.
[11] 董坤.基于协同过滤算法的高校图书馆图书推荐系统研究[J].现代图书情报技术,2011(11):44-47.
[12] 李卫华,卢雨民,梅红.浅谈数字图书馆个性化信息推荐系统[J].科技广场,2007(9):109-110.
[13] 姚望.面向学生的高校图书馆图书推荐系统[J].皖西学院学报,2014(4):149-152.
[14] 谢琳惠.推荐系统在高校数字图书馆的应用研究[J].现代情报,2006(11):72-74.
[15] 朱岩,林泽楠.电子商务中的个性化推荐方法评述[J].中国软科学,2009(2):183-192.
[16] DALTON S,刘燕权.推荐系统适用于图书馆吗?[J].图书情报工作,2007,51(12):19-25.
[17] 田野,祝忠明,刘树栋.基于关联数据的推荐系统综述[J].现代图书情报技术,2013(10):1-7.
[18] HURLEY N,ZHANG M I.Novelty and diversity in top-n recommendation-analysis and evaluation[J].ACM transactions on Internet technology,2011,10(4):1-30.
[19] ZHANG M I,HURLEY N.Avoiding monotony:improving the diversity of recommendation lists[C]//Proceedings of the ACM conference on recommender systems.New York: ACM,2008:123-130.
[20] 王国霞,王丽君,刘贺平.个性化推荐系统隐私保护策略研究进展[J].计算机应用研究,2012(6):2001-2008.
