情报研究

知识找回场景下推荐系统模拟实现及评价研究

  • 程秀峰 ,
  • 张孜铭 ,
  • 孟亚琪 ,
  • 范晓莹 ,
  • 杨金庆
展开
  • 华中师范大学信息管理学院 武汉 430079
程秀峰(ORCID:0000-0003-2139-2122),副教授,博士,硕士生导师;张孜铭(ORCID:0000-0002-3341-5574),本科生;孟亚琪(ORCID:0000-0002-4017-7180),本科生;范晓莹(ORCID:0000-0003-0369-8312),本科生。

收稿日期: 2018-10-19

  修回日期: 2019-01-23

  网络出版日期: 2019-08-20

基金资助

本文系国家自然科学青年项目"基于QSIM的图书馆移动用户群体行为模拟与学习兴趣引导研究"(项目编号:71503097)和华中师范大学基本科研业务费资助项目"基于上下文感知技术的交互式移动学习行为研究"(项目编号:CCNU18TS039)研究成果之一。

An Experimental Study on Simulation and Evaluation of Recommendation Systems for Knowledge Re-finding

  • Cheng Xiufeng ,
  • Zhang Ziming ,
  • Meng Yaqi ,
  • Fan Xiaoying ,
  • Yang Jinqing
Expand
  • School of Information Management, Central China Normal University, Wuhan 430079

Received date: 2018-10-19

  Revised date: 2019-01-23

  Online published: 2019-08-20

摘要

[目的/意义]信息过载一直是知识工作者在搜集、处理和创造知识的过程中所面临的主要困境。这种困境导致的结果之一是很难回忆起曾经使用过的文档的内容细节及具体位置,而推荐系统则能减少这样的困难。通过研究对比不同推荐系统在这一任务下的优缺点,可以帮助知识工作者更好地完成回忆任务。[方法/过程]基于相关理论,在同一场景(知识找回)模拟实现并测试了4种不同类型的推荐过程,包括基于内容的推荐CBR、基于协同过滤的推荐CFR、基于推理网络的推荐INR与融入了情境感知的推荐CAS,根据所确定的若干指标(精确性、情境相关性、预测性、多样性)对推荐效果进行比较。[结果/结论]结果显示,以上推荐系统在帮助用户回忆并找回文档过程中都有各自的优势,而基于情境感知的推荐系统在情境相关性与预测用户行为方面具有较好的效果。

本文引用格式

程秀峰 , 张孜铭 , 孟亚琪 , 范晓莹 , 杨金庆 . 知识找回场景下推荐系统模拟实现及评价研究[J]. 图书情报工作, 2019 , 63(16) : 72 -83 . DOI: 10.13266/j.issn.0252-3116.2019.16.008

Abstract

[Purpose/significance] Information overload has been always considered as the major barrier confronted by knowledge workers in the process of gathering, processing and producing information. One of its consequences is that it is hard to recall documents that ever used, while the recommendation system could reduce such difficulty. Comparing the recommendation efficiencies through representative recommendation mechanisms may assisst knowledge workers in accomplishing the task of knowledge re-finding.[Method/process] Based on associated recommendation system theoies, this paper presents a simulation on 4 different recommendation procedures in an unified experimental scene(knowledge re-finding), the precedures includes CBR, CFR, INR and CAS. 4 evaluation criteria (precision, context-relevance, action-prediction, diversity) has been used to evaluate and compare the efficiency of corresponding recommendation systems.[Result/conclusion] The results show that each recommendation procedure has its own advantages in knowledge re-finding from different perspectives, and CAS has advantages in both context-relevance and action-prediction.

参考文献

[1] BAWDEN D, ROBINSON L.The dark side of information:overload, anxiety and other paradoxes and pathologies[J]. Journal of information science, 2009, 35(2):180-191.
[2] RICCI F, ROKACH L, SHAPIRA B, et al. Recommender systems handbook[M]. Berlin:Springer, 2011.
[3] SCHAFER J B, DAN F, HERLOCKER J, et al. Collaborative filtering recommender systems[M]. Berlin:Springer, 2007.
[4] BELL R M, KOREN Y. Scalable collaborative filtering with jointly derived neighborhood interpolation weights[C]//Proceedings of the seventh IEEE international conference on data mining. Washington:IEEE Computer Society, 2007:43-52.
[5] MANOUSELIS N, VUORIKARI R, ASSCHE F V. Collaborative recommendation of e-learning resources:an experimental investigation[J]. Journal of computer assisted learning, 2010, 26(4):227-242.
[6] 熊回香,杨雪萍,高连花,等.基于用户兴趣主题模型的个性化推荐研究[J].情报学报,2017,36(9):916-928.
[7] 王玙,刘东苏.基于联合聚类与用户特征提取的协同过滤推荐算法[J].情报学报,2017,36(8):852-858.
[8] DOAN A H. Learning to map between ontologies on the semantic web[C]//Proceedings of the eleventh international conference on World Wide Web. New York:ACM, 2002:622-673.
[9] BRASETHVIK T, GULLA J A. Natural language analysis for semantic document modeling[J]. Data & knowledge engineering, 2001, 38(1):45-62.
[10] KIM J H, SONG C W, LIM K W, et al. Design of music recommendation system using context information[C]//Proceedings of the 2006 Pacific Rim international conference on agent computing & multi-agent systems. Berlin:Springer, 2006:708-713.
[11] 王玙, 刘东苏.基于联合聚类与用户特征提取的协同过滤推荐算法[J].情报学报, 2017, 36(8):852-858.
[12] MA H, ZHOU T C, LYU M R, et al. Improving recommender systems by incorporating social contextual information[J]. ACM transactions on information systems, 2011, 29(2):1-23.
[13] LIU N N, HE L, ZHAO M. Social temporal collaborative ranking for context aware movie recommendation[J]. ACM transactions on intelligent systems and technology, 2013, 4(1):1-26.
[14] WANG X, ROSENBLUM D, WANG Y. Context-aware mobile music recommendation for daily activities[C]//Proceedings of the 20th ACM multimedia. New York:ACM, 2012:99-108.
[15] ELSWEILER D, RUTHVEN I, JONES C. Towards memory supporting personal information management tools[J]. Journal of the American Society for Information Science & Technology, 2007, 58(7):924-946.
[16] REINHARDT W, SCHMIDT B, SLOEP P, et al. Knowledge worker roles and actions-results of two empirical studies[J]. Knowledge & process management, 2011, 18(3):150-174.
[17] WANG W, LI W, WU Z, et al. An ontology-based context model for building context-aware services[C]//Procedings of the second international conference on intelligent systems, Modelling and Simulation. Washington:IEEE Computer Society, 2011:296-299.
[18] WAKELING S, CLOUGH P, SEN B. Investigating the potential impact of non-personalized recommendations in the OPAC:Amazon vs WorldCat.org[C]//Proceedings of the fifth information interaction in context symposium. New York:ACM, 2014:96-105.
[19] CHARI S, CHRISTODOULIDES G, PRESI C, et al. Consumer trust in user-generated brand recommendations on Facebook[J]. Psychology & marketing, 2016, 33(12):1071-1081.
[20] SAPPELLI M, VERBERNE S, KRAAIJ W. Evaluation of context-aware recommendation systems for information re-finding[J]. Journal of the Association for Information Science & Technology, 2017, 68(4):895-910.
[21] AULA A. Information search and re-access strategies of experienced web users[C]//Proceedings of the 14th international conference on World Wide Web. New York:ACM, 2005:583-592.
[22] TEEVAN J, ADAR E, JONES R, et al. Information re-retrieval:repeat queries in Yahoo's logs[C]//Proceedings of the 2007 International ACM Sigir conference on research & development in information retrieval. New York:ACM, 2007:151-158.
[23] OBENDORF H, WEINREICH H, HERDER E, et al. Web page revisitation revisited:implications of a long-term click-stream study of browser usage[C]//Proceedings of the 2007 SIGCHI conference on human factors in computing systems. New York:ACM, 2007:597-606.
[24] TAUSCHER L, GREENBERG S. Revisitation patterns in World Wide Web navigation[C]//Proceedings of the 1997 ACM SIGCHI conference on human factors in computing systems. New York:ACM, 1997:399-406.
[25] COCKBURN A, MCKENZIE B. What do web users do? an empirical analysis of web use[J]. International journal of human-computer studies, 2001, 54(6):903-922.
[26] WEN J. Post-valued recall web pages:user disorientation hits the big time[J]. IT & society, 2003, 1(3):184-194.
[27] HARPER S. Integrating memory context into personal information re-finding[C]//Proceedings of the 2nd BCS-IRSG conference on future directions in information access. London:British Computer Society, 2008:14-21.
[28] DENG T, ZHAO L, WANG H, et al. ReFinder:a context-based information refinding system[J]. IEEE transactions on knowledge & data engineering, 2013, 25(9):2119-2132.
[29] VÖLKEL M, ABECKER A. Cost-benefit analysis for the design of personal knowledge management systems[J]. Proc of ICEIS, 2009, 6030(1):95-105.
[30] GOLDBERG D. Using collaborative filtering to weave an information tapestry[J].Communications of the ACM, 1992, 35(12):61-70.
[31] RESNICK P, IACOVOU N, Suchak M, et al. GroupLens:an open architecture for collaborative filtering of netnews[C]//Proceedings of the 1994 ACM conference on computer supported cooperative work. New York:ACM, 1994:175-186.
[32] 阮光册, 夏磊.推荐系统的发展与公共图书馆个性化信息服务探讨[J].图书馆, 2016, 2016(2):94-99.
[33] BAEZA-YATES R, RIBEIRO-NETO B. Modern Information Retrieval[M]. New York:ACM Press, 1997.
[34] RESNICK P, VARIAN H R. Recommender systems[J]. Communications of the ACM, 1997, 40(3):56-58.
[35] LI Y, LU L, LI X. A hybrid collaborative filtering method for multiple-interests and multiple-content recommendation in E-Commerce[J]. Expert systems with applications, 2005, 28(1):67-77.
[36] JI A T, YEON C, KIM H N, et al. Collaborative tagging in recommender systems[M]. Berlin:Springer, 2007.
[37] WOOLDRIDGE M J. An Introduction to Multiagent Systems[M]. Chichester:John Wiley & Sons, 2002.
[38] ADOMAVICIUS G. Incorporating contextual information in recommender systems using a multidimensional approach[J]. ACM transactions on information systems, 2005, 23(1):103-145.
[39] LI Y, ZHANG D, LAN Z, et al. Context-aware advertisement recommendation for high-speed social news feeding[C]//Proceedings of the 2016 international conference on data engineering. Washington:IEEE Computer Society, 2016:505-516.
[40] LOMMATZSCH A. Real-time news recommendation using context-aware ensembles[C]//Proceedings of the 2014 European conference on information retrieval. Berlin:Springer, 2014:51-62.
[41] GOLDBERG D. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12):61-70.
[42] IEHistoryView[EB/OL].[2017-09-24] https://iehistoryview.en.softonic.com/.
[43] GOLDBERG D, NICHOLS D, OKI B, et al. Using collaborative filtering to weave an information tapestry[J]. Communications of the ACM, 1992, 35(12), 61-70.
[44] AHN H J.A new similarity measure for collaborative filtering to alleviate the new user cold-starting problem[J].Information sciences, 2008, 178(1):37-51.
[45] NAGARA R, SCUTARI M, LÉBRE S. Bayesian network inference algorithms[M]. Berlin:Springer, 2013.
[46] TURTLE H, CROFT W B.Evaluation of an inference network-based retrieval model[M]. New York:ACM, 1991.
[47] STROHMAN T, METZLER D, TURTLE H, et al. Indri:a language-model based search engine for complex queries[C]//Proceedings of 2005 IEEE international conference on information and automation. New York:ACM, 2005:1-34.
[48] MCCLELLAND J L, RUMELHART D E. An interactive activation model of context effects in letter perception,part i:an account of basic findings[J].Psychological review, 2013, 88(5):375-407.
[49] CRESTANI F.Application of spreading activation techniques in information retrieval[M]. Dordrecht:Kluwer Academic Publishers, 1997.
[50] 田野, 杨眉, 祝忠明, 等.关联数据驱动的查询扩展技术研究[J]. 图书情报工作, 2015, 59(4):122-128.
[51] DEY A K, ABOWD G D. CybreMinder:a context-aware system for supporting reminders[C]//Proceedings of the 2nd international symposium on handheld and ubiquitous computing. Berlin:Springer, 2000:172-186.
[52] LÜ L Y, MEDO M, CHI H Y, et al. Recommender systems[J]. Physics reports, 2012, 519(1):1-49
[53] FLICK C. ROUGE:A package for automatic evaluation of summaries[C]//Proceedings of the workshop on text summarization branches out. Stroudsburg:ACL, 2004:1-105.
文章导航

/