计算机科学 ›› 2019, Vol. 46 ›› Issue (8): 78-83.doi: 10.11896/j.issn.1002-137X.2019.08.012

• 大数据与数据科学* • 上一篇    下一篇

项目多属性模糊联合的多样性视频推荐算法

张艳红1, 张春光2, 周湘贞3, 王怡鸥4   

  1. (广东技术师范大学天河学院计算机科学与工程学院 广州510540)1
    (北京科技大学计算机与通信工程学院 北京100083)2
    (北京航空航天大学计算机学院 北京100191)3
    (北京市科学技术情报研究所 北京100044)4
  • 收稿日期:2019-03-04 发布日期:2019-08-15
  • 通讯作者: 张艳红(1978-),女,硕士,讲师,主要研究方向为大数据分析、推荐算法,E-mail:33582210@qq.com
  • 作者简介:张春光(1976-),男,博士,讲师,主要研究方向为人工智能、推荐算法、计算机网络;周湘贞(1976-),女,博士,副教授,主要研究方向为图像处理、推荐算法;王怡鸥(1990-),女,博士,助理研究员,主要研究方向为情报研究、智能信息处理
  • 基金资助:
    国家自然科学基金面上项目(61672077),广东省教育厅教育科学规划教育信息技术研究项目(14JXN060),广东省教育厅项目(2017SZ03)

Diverse Video Recommender Algorithm Based on Multi-property Fuzzy Aggregate of Items

ZHANG Yan-hong1, ZHANG Chun-guang2, ZHOU Xiang-zhen3, WANG Yi-ou4   

  1. (School of Computer Science and Engineering,Tianhe College of Guangdong Polytechnic Normal University,Guangzhou 510540,China)1
    (School of Computer & Communication Engineering,University of Science Technology,Beijing 100083,China)2
    (School of Computer Science and Engineering,Beihang University,Beijing,100191,China)3
    (Beijing Institute of Science and Technology Information,Beijing 100044,China)4
  • Received:2019-03-04 Published:2019-08-15

摘要: 针对视频协同过滤推荐算法多样性较低的问题,提出了一种基于多属性联合的多样性视频协同过滤推荐算法。根据用户与推荐系统的互动历史记录,判断用户是否满意系统的推荐项目,如果某个用户过去观看同一个主题的视频节目,并且不关心视频的作者,那么认为该用户对视频作者表现出较高的多样性,对视频节目主题表现出的多样性较低。采用信息熵与用户配置信息长度两个指标来评估项目各个属性的多样性,根据两个指标的组合将用户对每个项目属性的多样性分为4个象限,并且对用户多样性进行模糊化处理,以获得用户多样性对于4个象限的隶属度。在第一个阶段预测未评分项目的评分;在第二个阶段将所有项目重新排序,以提高推荐列表的多样性。最终,基于公开的Movielens 1M数据集进行了对比实验,实验结果证明本算法可实现接近top-N算法的准确率性能,同时具有一定的多样性增强效果。在推荐准确率与多样性平衡的应用场景下,设置合适的参数能够在损失较少推荐准确率的前提下,显著提高个体多样性、总体多样性与新颖性。

关键词: 电子商务, 视频推荐系统, 多样性增强, 协同过滤推荐算法, 重新排序算法, 长尾分布

Abstract: In order to improve the diversity of the collaborative filtering recommender system of videos,this paper proposed a diverse videos collaborative filtering recommender algorithm based on multi-property aggregate.According to the history of interaction between users and recommendation system,users are judged whether they are satisfied with the recommendation items of the system.If a user watches the videos on the same topic produced by different video authors,it indicates that this user shows high diversity to the video authors,and low diversity to the video subjects.Information entropy and user profile length are used to evaluate the diversity of each item’s attributes.According to the combination of the two indicators,the user’s diversity of each item’s attributes is divided into four quadrants,and the user’s diversity is fuzzified to obtain the membership degree of user’s diversity to the four quadrants.In the first phase,it predicts the rates of unrated items.In the second phase,it re-ranks all items,which improves the diversity of recommendation list.At last,experimental results based on the public Movielens 1M dataset show that,the proposed algorithm can realize the similar accuracy with top-N algorithm,at the same time,it enhances the diversity effectively.In the application scenario of balancing recommendation accuracy and diversity,setting appreciate parameters can improve the individual diversity,total diversity and freshness significantly with acceptable recommendation accuracy reduction

Key words: Electronic commerce, Video recommender system, Diversity enhancement, Collaborative filtering recommender algorithm, Re-ranking algorithm, Long tail distribution

中图分类号: 

  • TP391
[1] ZHUO Y,YOU J L,WANG J L,et al.Measurement and Re- commendation System Oriented to Online Video Service in Sea Service[J].Computer Engineering,2018,44(4):28-34,40.(in Chinese) 卓煜,尤佳莉,王劲林,等.海服务中面向在线视频服务的测量与推荐系统[J].计算机工程,2018,44(4):28-34,40.
[2] WANG X,NIE X,WANG X,et al.A new recommender system framework for TV video[C]∥International Conference on Information Science & Technology.IEEE,2016:147-152.
[3] SHI M Z,WU G D,ZHANG Q,et al.Research on the Long Tail Distribution Recommendation of the Multi-topic and RBM[J].Journal of Chinese Computer Systems,2018,39(2):304-309.(in Chinese) 史明哲,吴国栋,张倩,等.多主题受限玻尔兹曼机的长尾分布推荐研究[J].小型微型计算机系统,2018,39(2):304-309.
[4] D EZ J,MART NEZ-REGO D,ALONSO-BETANZOS A,et al.Optimizing novelty and diversity in recommendations[J].Progress in Artificial Intelligence,2018,1(3):1-9.
[5] BENHAMOU F.Fair use and fair competition for digitized cultural goods:the case of eBooks[J].Journal of Cultural Econo-mics,2015,39(2):123-131.
[6] SHEUGH L,ALIZADEH S H.A novel 2D-Graph clustering method based on trust and similarity measures to enhance accuracy and coverage in recommender systems[J].Information Scien-ces,2018,432(1):210-230.
[7] WANG S.A recommendation algorithm based on aggregate diversity enhancement[J].Computer Engineering and Science,2016,38(1):183-187.(in Chinese) 王森.一种基于整体多样性增强的推荐算法[J].计算机工程与科学,2016,38(1):183-187.
[8] REN C,PING Z,HUA Z.A new Collaborative Filtering technique to improve recommendation diversity[C]∥IEEE International Conference on Computer & Communications.2017.
[9] DI NOIA T,OSTUNI V C,ROSATI J,et al.An analysis of users’ propensity toward diversity in recommendations[C]∥Proceedings of the 8th ACM Conference on Recommender systems.ACM,2014:285-288.
[10] HE M,XIAO R,LIU W S,et al.Collaborative Filtering Recommendation Algorithm Combing Category Information and User Interests[J].Computer Science,2017,44(8):236-241.(in Chinese) 何明,肖润,刘伟世,等.融合类别信息和用户兴趣度的协同过滤推荐算法[J].计算机科学,2017,44(8):236-241.
[11] WEN J H,YUAN P L,ZENG J,et al.Research on Collaborative Filtering Recommendation Algorithm Based on Topic of Tags[J].Computer Engineering,2017,43(1):247-252.(in Chinese) 文俊浩,袁培雷,曾骏,等.基于标签主题的协同过滤推荐算法研究[J].计算机工程,2017,43(1):247-252.
[12] BRAUNHOFER M,ELAHI M,RICCI F.Alleviating the new user problem in collaborative filtering by exploiting personality information[J].User Modeling and User-Adapted Interaction,2016,26(2/3):221-255.
[13] REN C,PING Z,HUA Z.A new Collaborative Filtering technique to improve recommendation diversity[C]∥IEEE International Conference on Computer & Communications.2017.
[14] GOGNA A,MAJUMDAR A.Balancing accuracy and diversity in recommendations using matrix completion framework[J].Knowledge-Based Systems,2017,125(1):83-95.
[15] CARBONELL J,GOLDSTEIN J.The use of MMR,diversity-based reranking for reordering documents and producing summaries[C]∥International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,1998:335-336.
[16] ULLAH M Z,SHAJALAL M,CHY A N,et al.Query Subtopic Mining Exploiting Word Embedding for Search Result Diversification[C]∥Asia Information Retrieval Symposium.Cham:Springer,2016:308-314.
[17] RAN J,LEJEUNE M A.Risk-budgeting multi-portfolio optimization with portfolio and marginal risk constraints[J].Annals of Operations Research,2018,262(2):1-32.
[18] OSTUNI V C,NOIA T D,SCIASCIO E D,et al.Top-N recommendations from implicit feedback leveraging linked open data[C]∥ACM Conference on Recommender Systems.ACM,2013:85-92.
[19] CLARKE C L A,KOLLA M,CORMACK G V,et al.Novelty and diversity in information retrieval evaluation[C]∥International ACM SIGIR Conference on Research and Development in Information Retrieval.ACM,2008:659-666.
[20] NIKOLAKOPOULOS A N,KALANTZIS V,GALLOPOULOS E,et al.Factored Proximity Models for Top-N Recommendations[C]∥IEEE International Conference on Big Knowledge.2017.
[21] CASTELLS P.Improving sales diversity by recommending users to items[C]∥ACM Conference on Recommender Systems.ACM,2014:145-152.
[22] ZHANG Z,FAN X Y,GUO Y T,et al.Dynamic Summarization Update Method Based on Topic Signature[J].Computer Engineering,2018,44(6):169-175.(in Chinese) 张祯,樊兴悦,郭禹田,等.基于Topic Signature的动态文摘更新方法[J].计算机工程,2018,44(6):169-175.
[23] YU X S,SUN S.Research on Personalized Recommendation Model Based on Network Users’ Information Behavior.Journal of Chongqing University of Technology(Natural Science),2013,27(1):47-50.(in Chinese) 余肖生,孙珊.基于网络用户信息行为的个性化推荐模型.重庆理工大学学报(自然科学),2013,27(1):47-50.
[24] WANG Y,WAN X Y,TAO Y Z,et al.Collaborative filtering recommendation algorithm based on K-medoids item clustering.Journal of Chongqing University of Posts and Telecommunications(Natural Science Edition),2017,29(4):521-526.(in Chinese) 王永,万潇逸,陶娅芝,等.基于K-medoids项目聚类的协同过滤推荐算法.重庆邮电大学学报(自然科学版),2017,29(4):521-526.
[1] 黄涛,黄仁,张坤. 一种改进的协同过滤推荐算法[J]. 计算机科学, 2016, 43(Z6): 400-403.
[2] 李道全,吴兴成,郭瑞敏. 一种基于二层节点和客观风险的电子商务交易信任模型[J]. 计算机科学, 2016, 43(5): 117-121.
[3] 石宏彬,郭克华. 基于感知哈希与用户偏好的检索意图建模方法[J]. 计算机科学, 2016, 43(3): 305-308.
[4] 张莉,余磊. 推荐系统中谁可以协同新用户?[J]. 计算机科学, 2015, 42(Z11): 80-82.
[5] 郑炅,石 刚. 基于用户间动态信任关系的推荐算法研究[J]. 计算机科学, 2015, 42(9): 230-234.
[6] 马霄,甘早斌,鲁宏伟,马尧. 电子商务中的一种潜在信任关系预测方法[J]. 计算机科学, 2014, 41(12): 138-142.
[7] 张小玲,秦凤梅,邱玉辉. 电子商务网站界面色彩情感的导向性研究[J]. 计算机科学, 2013, 40(Z11): 415-416,438.
[8] 李俊,薛伟,甘旭阳. 基于EigenRep信任模型的一种改进信任机制[J]. 计算机科学, 2013, 40(7): 113-115.
[9] 肖仕成,李开,甘早斌. 基于四方的安全电子商务支付协议分析与验证[J]. 计算机科学, 2012, 39(3): 75-78.
[10] 熊建英,钟元生. 一种抗欺诈的C2C卖方信誉计算模型研究[J]. 计算机科学, 2012, 39(2): 68-71.
[11] 樊丽杰,王素贞,刘卫. 基于人类信任机制的移动电子商务信任评估方法[J]. 计算机科学, 2012, 39(1): 190-192,214.
[12] 范波,程久军. 用户间多相似度协同过滤推荐算法[J]. 计算机科学, 2012, 39(1): 23-26.
[13] 甘早斌,肖仕成,李开,肖国强. 基于四方的安全电子商务支付协议研究[J]. 计算机科学, 2011, 38(10): 39-44.
[14] 郭华,李舟军,庄雷,计宏霖. 一种新的电子商务协议分析方法[J]. 计算机科学, 2010, 37(8): 56-60.
[15] 田伟,许静,彭玉青. 基于离散评分向量概率分析的CF算法改进研究[J]. 计算机科学, 2010, 37(5): 181-183.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
[1] 胡庆成, 张勇, 邢春晓. 基于有重叠社区划分的社会网络影响最大化方法研究[J]. 计算机科学, 2018, 45(6): 32 -35 .
[2] 郑香平, 於志勇, 温广槟. 地点网络中的社区发现[J]. 计算机科学, 2018, 45(6): 46 -50 .
[3] 朱文强. 面向O2O服务的移动社交网络个性化可信群体识别模型[J]. 计算机科学, 2018, 45(6): 76 -83 .
[4] 陈翔, 王秋萍. 基于代码修改的多目标有监督缺陷预测建模方法[J]. 计算机科学, 2018, 45(6): 161 -165 .
[5] 冉正, 罗蕾, 晏华, 李允. 基于纳什均衡的AUTOSAR任务到多核ECU的映射方法[J]. 计算机科学, 2018, 45(6): 166 -171,182 .
[6] 林伟俊, 赵辽英, 厉小润. 基于逐像素递归处理的高光谱实时亚像元目标检测[J]. 计算机科学, 2018, 45(6): 259 -264 .
[7] 刘玉成, 理查德·丁, 张颖超. 一种BPNNs识别算法的医学检测泛实时性问题研究[J]. 计算机科学, 2018, 45(6): 301 -307 .
[8] 许文浩,沈航,白光伟. 无线链路质量突变性感知的机会路由协议[J]. 计算机科学, 2018, 45(5): 83 -88 .
[9] 于阳,于洪涛,黄瑞阳. 基于多重信任的协同过滤推荐算法[J]. 计算机科学, 2018, 45(5): 108 -115 .
[10] 郑剑炜,顾晶晶,庄毅. 基于生存分析的GPS轨迹缺失规律挖掘[J]. 计算机科学, 2018, 45(5): 185 -189 .