[目的/意义]针对基于内容的个性化推荐策略,提出资源特征选择与权值计算优化策略,从而改善个性化推荐的效果。[方法/过程]构建基于用户决策机理的个性化推荐模型,模型以用户决策机理为背景知识进行资源特征的选择、用户兴趣模型的构建与语义表示、用户决策函数构建。为验证模型效果,以4 748位用户的观影数据为例进行实验,实验以向量空间模型为参照模型,P@N为评价指标。[结果/结论]实验结果显示,在N取值为5、10、20、50、100、200的情况下,基于用户决策机理的个性化推荐模型效果都显著优于向量空间模型,从而验证模型的有效性。
Abstract
[Purpose/significance] The purpose of this paper is to propose an optimization strategy of features choosing and weight computing for content-based personalized recommendation.[Method/process] This paper proposes a personalized recommendation model based on user's decision-making mechanism, which takes user decision mechanism as background knowledge in features selection, user interest profile construction and semantic representation, and user decision function construction. To test this model, this paper conducts an experiment taking 4 748 users as sample, vector space model as reference model, and P@N as evaluation index.[Result/conclusion] The results show that, in the cases of N equals 5, 10, 20, 50, 100, 200, the personalized recommendation model based on user decision-making mechanism is significantly better than the vector space model, and the effectiveness of the model is verified.
关键词
决策机理 /
基于内容推荐 /
个性化推荐
{{custom_keyword}} /
Key words
decision-making mechanism /
content-based recommendation /
personalized recommendation
{{custom_keyword}} /
中图分类号:
G203
{{custom_clc.code}}
({{custom_clc.text}})
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] LU J, WU D, MAO M, et al. Recommender system application developments:a survey[J]. Decision support systems, 2015, 74(C):12-32.
[2] 阮光册, 夏磊. 互联网推荐系统研究综述[J]. 情报学报, 2015, 34(9):999-1008.
[3] KUNAVER M, Pozrl T. Diversity in recommender systems-a survey[J]. Knowledge-based systems, 2017, 123(9):154-162.
[4] HARIRI N, MOBASHER B, BURKE R. Context adaptation in interactive recommender systems[C]//ACM conference on recommender systems. New York:ACM, 2014:41-48.
[5] 王东山. 消费者购买决策理论评述与展望[J]. 商业经济研究, 2017(21):43-46.
[6] 李宗伟, 张艳辉, 栾东庆. 哪些因素影响消费者的在线购买决策[J]. 管理评论, 2017, 29(8):136-146.
[7] LAY-YEE K L, HAN K S, FAH B C Y. Factors affecting smartphone purchase decision among malaysian generation Y[J]. International journal of Asian social science, 2013, 3(12):2426-2440.
[8] SUJATA J, YATIN J, ABHIJIT C, et al. Factors affecting smartphone purchase among Indian youth:a descriptive analysis[J]. Indian journal of science & technology, 2016, 9(15):1-10.
[9] JOO S, CHOI N. Factors affecting undergraduates' selection of online library resources in academic tasks[J]. Library Hi Tech, 2015, 33(2):114-117.
[10] 查先进, 李力, 严亚兰, 等. 数字图书馆环境下信息有用性和信息获取影响因素研究[J]. 情报学报, 2017, 36(7):669-681.
[11] 吴江, 周露莎. 网络健康信息服务用户购买决策的影响因素研究[J]. 情报学报, 2017, 36(10):1058-1065.
[12] BOGDANOV D, HARO M, FUHRMANN F, et al. Semantic audio content-based music recommendation and visualization:based on user preference examples[J]. Information processing & management, 2013, 49(1):13-33.
[13] 谭学清, 何珊. 音乐个性化推荐系统研究综述[J]. 现代图书情报技术, 2014, 30(9):22-32.
[14] 洪文, 聂延平, 青巧. 馆藏资源自动推荐模型结构与处理流程优化分析[J]. 情报理论与实践, 2016, 39(5):130-133.
[15] SOARES M, VIANA P. Tuning metadata for better movie content-based recommendation systems[J]. Multimedia tools and applications, 2015, 74(17):7015-7036.
[16] JUN S, KIM D, JEON M, et al. Social mix:automatic music recommendation and mixing scheme based on social network analysis[J]. Journal of supercomputing, 2015, 71(6):1933-1954.
[17] CHEN C, CHEN C, CHEN H, et al. Towards context-aware social recommendation via individual trust[J]. Knowledge-based systems, 2017, 127(C):58-66.
[18] ÅMAN P, LⅡKKANEN L A. Interacting with context factors in music recommendation and discovery[J]. International journal of human-computer interaction, 2017,33(3):165-179.
[19] 李江, 李东, 冯培桦, 等. 基于专长吻合度、学术影响力与社会关联值的专家推荐模型研究[J]. 情报学报, 2017, 36(4):338-345.
[20] 杨程, 范强, 王涛, 等. 基于多维特征的开源项目个性化推荐方法[J]. 软件学报, 2017, 28(6):1357-1372.
[21] 周建中, 徐芳. 国立科研机构同行评议方法的模式比较研究[J]. 科学学研究, 2013, 31(11):1642-1648.
[22] 庄锦英.决策心理学[M].上海:上海教育出版社,2006:12-16.
[23] HAN J, KAMBER M, PEI J. 数据挖掘概念与技术[M]. 3版.范明,孟小峰, 译.北京:机械工业出版社, 2012:55-79.
[24] 林鑫, 石宇, 周知. 基于相对频次的标签相关性判断优化研究[J]. 图书情报工作, 2016,60(17):130-135.
[25] 吕学强, 王腾, 李雪伟, 等. 基于内容和兴趣漂移模型的电影推荐算法研究[J/OL].[2017-11-21]. http://www.arocmag.com/article/02-2018-03-049.html.
[26] ÇATALTEPE Z, ULUYAGMUR M, TAYFUR E. Feature selection for movie recommendation[J]. Turkish journal of electrical engineering & computer sciences, 2016, 24(3):833-848.
[27] SHI C, LIU J, ZHUANG F, et al. Integrating heterogeneous information via flexible regularization framework for recommendation[J]. Knowledge & information systems, 2015, 49(3):835-859.
[28] 胡潜, 林鑫. 社会化标注系统中基于标签和项目的兴趣建模比较研究[J]. 情报学报, 2015, 34(12):1296-1303.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
本文系国家社会科学基金青年项目"社会网络中基于用户认知结构的知识标注研究"(项目编号:17CTQ024)研究成果之一。
{{custom_fund}}