基于子组与社会行为的缩小群组推荐列表方法

doi:10.11896/j.issn.1002-137X.2019.02.031

计算机科学 ›› 2019, Vol. 46 ›› Issue (2): 202-209.doi: 10.11896/j.issn.1002-137X.2019.02.031

基于子组与社会行为的缩小群组推荐列表方法

毛宇佳, 刘学军, 徐新艳, 张欣

南京工业大学计算机科学与技术学院南京211816

收稿日期:2018-06-14 出版日期:2019-02-26 发布日期:2019-02-26
通讯作者: 刘学军(1971-),男,博士,教授,CCF高级会员,主要研究方向为数据库、数据挖掘、推荐系统等,E-mail:lxj_njgd@163.com;
作者简介:毛宇佳(1994-),男,硕士生,主要研究方向为数据挖掘、推荐系统,E-mail:myj.mao@qq.com;徐新艳(1980-),女,硕士,讲师,主要研究方向为数据挖掘、智能信息处理;张欣(1994-),女,硕士生,主要研究方向为机器学习、推荐系统等。
基金资助:
本文受国家重点研发计划子课题(2017YFC0805605),江苏省重点研发计划项目(BE2015697,BE2017617)资助。

Method Based on Sub-group and Social Behavior for NarrowingRecommended List for Groups

MAO Yu-jia, LIU Xue-jun, XU Xin-yan, ZHANG Xin

College of Computer Science and Technology,Nanjing Tech University,Nanjing 211816,China

Received:2018-06-14 Online:2019-02-26 Published:2019-02-26

摘要/Abstract

摘要： 以多个用户为推荐对象的组推荐系统已成为研究热点。目前,组推荐系统大多考虑如何充分挖掘用户偏好来尽可能满足所有用户的需求,但这也造成了推荐列表规模过大的问题,从而导致群组成员无法快速做出决定。针对该问题,文中提出了一种缩小群组推荐列表的方法(Recommendation Method based on Sub-Group and Social Behavior,RMSGSB)。该方法通过划分子组来缩小群组规模并减少群组偏好属性数量,利用成员的社会行为,从容忍度与利他行为两方面为子组分配权重,以保证推荐公平性。在真实数据集上的实验对比结果表明,该算法具有更好的群组推荐效果。

关键词: 利他行为, 群组推荐, 容忍度, 推荐列表, 子组

Abstract: Group recommend systems have been drawn a lot of attention for their capability of targeting users’ prefe-rence to satisfy all the users’ requirements,which cause the problem that the recommended list is too large simulta-neously,thus making it hard for group members to make their decisions.Regarding current issues,a method for narrowing the recommended list for groups called RMSGSB(A Recommendation Method based on Sub-group and Social Behavior) was proposed.In order to narrow the group scale and the amount of group preferences,the method divides the target group into several sub-groups.For guaranteeing the fairness of recommending,the weight of sub-groups is catculated according to the tolerance and altruism of group members’ social behavior.Based on real date set,the experiment results show that the proposed method has better performance than other methods on group recommendation.

Key words: Altruism, Group recommendation, Recommended list, Sub-group, Tolerance

中图分类号:

TP391

毛宇佳, 刘学军, 徐新艳, 张欣. 基于子组与社会行为的缩小群组推荐列表方法[J]. 计算机科学, 2019, 46(2): 202-209. https://doi.org/10.11896/j.issn.1002-137X.2019.02.031

MAO Yu-jia, LIU Xue-jun, XU Xin-yan, ZHANG Xin. Method Based on Sub-group and Social Behavior for NarrowingRecommended List for Groups[J]. Computer Science, 2019, 46(2): 202-209. https://doi.org/10.11896/j.issn.1002-137X.2019.02.031

参考文献

[1]O’CONNOR M,DAN C,KONSTAN J A,et al.PolyLens:A Recommender System for Groups of Users[C]∥ Conference on European Conference on Computer Supported Cooperative Work.Netherlands:Springer,2001:199-218.
[2]FENG S,CAO J.Improving group recommendations via detecting comprehensive correlative information[J].Multimedia Tools & Applications,2015,76(1):1-23.
[3]SYMEONIDIS P,TIAKAS E,MANOLOPOULOS Y.Product recommendation and rating prediction based on multi-modal social networks[C]∥Proceedings of the fifth ACM Conference on Recommender Systems.New York:ACM,2011:61-68.
[4]BAGCI H,KARAGOZ P.Context-Aware Friend Recommendation for Location Based Social Networks using Random Walk[C]∥ Proceedings of the 25th International Conference Companion on World Wide Web.Canada,2016:531-536.
[5]REN Z,LIANG S,LI P,et al.Social Collaborative Viewpoint Regression with Explainable Recommendations[C]∥ Procee-dings of the Tenth ACM International Conference on Web Search and Data Mining.New York:ACM,2017:485-494.
[6]HONG M,JUNG J J,CAMACHO D.GRSAT:A Novel Method on Group Recommendation by Social Affinity and Trustworthiness[J].Cybernetics & Systems,2017,48(3):140-161.
[7]YUAN Z,CHEN C.Research on group POIs recommendation fusion of users’ gregariousness and activity in LBSN[C]∥ IEEE International Conference on Cloud Computing and Big Data Analysis.China:IEEE,2017:305-310.
[8]LIN X,ZHANG M,ZHANG Y F,et al.Fairness-Aware Group Recommendation with Pareto-Efficiency[C]∥The Eleventh ACM Conference.New York:ACM,2017:107-115.
[9]WANG S,WANG Y,TANG J,et al.What Your Images Reveal:Exploiting Visual Contents for Point-of-Interest Recommendation[C]∥ Proceedings of the 26th International Con-ference on World Wide Web.Canada,2017:391-400.
[10]HE R,MCAULEY J.Ups and Downs:Modeling the Visual Evolution of Fashion Trends with One-Class Collaborative Filtering[C]∥ Proceedings of the 25th International Conference on World Wide Web.Canada,2016:507-517.
[11]LAI C H,HONG P R.Group Recommendation Based on the Analysis of Group Influence and Review Content[C]∥Asian Conference on Intelligent Information and Database Systems.Japan:Springer,Cham,2017:100-109.
[12]NAAMANI-DERY L,KALECH M,ROKACH L,et al.Pre- ference elicitation for narrowing the recommended list for groups[C]∥ Proceedings of the 8th ACM Conference onRe-commender systems.New York:ACM,2014:333-336.
[13]HUANG C H,YIN J,HOU F.A text similarity measurement combining word semantic information with TF-IDF method[J].Chinese Journal of Computers,2011,34(5):856-864.(in Chinese)
黄承慧,印鉴,侯昉.一种结合词项语义信息和TF-IDF方法的文本相似度量方法[J].计算机学报,2011,34(5):856-864.
[14]ZHANG Y J,DU Y L,MENG X W.Research on group recommendation systems and their application[J].Chinese Journal of Computers,2016,39(4):745-764.(in Chinese)
张玉洁,杜雨露,孟祥武.组推荐系统及其应用研究[J].计算机学报,2016,39(4):745-764.
[15]PESSEMIER T,DOOMS S,MARTENS L.Comparison of group recommendation algorithms[M].Dordrecht:Kluwer Academic Publishers,2014:2497-2541.
[16]KAGITA V R,PUJARI A K,PADMANABHAN V.Virtual user approach for group recommender systems using precedence relations[M].Tanytown:Elsevier Science Inc,2015:15-30.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于子组与社会行为的缩小群组推荐列表方法

Method Based on Sub-group and Social Behavior for NarrowingRecommended List for Groups

PDF (PC)

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 2

Metrics

本文评价

推荐阅读 0

[1]	王晓芳,谢仲文,李彤,成蕾,郑交交,刘晓芳. 一种带租户演化容忍度的SaaS服务演化一致性判定方法 Saas Service Evolution Consistency Checking with Tenant Tolerance 计算机科学, 2018, 45(5): 147-155. https://doi.org/10.11896/j.issn.1002-137X.2018.05.025
[2]	. 一种基于有限自动机的渐变镜头检测算法计算机科学, 2006, 33(1): 252-254.