基于用户—资源—词汇三部图的社会化推荐算法设计与实现
|
摘要
面向用户小众化需求和长尾资源特征的社会化推荐实现对于提升网络服务质量具有重要作用。文章根据物理动力学中物质扩散和热传导能量分配机理,并将词汇引入关联图中,探讨了基于用户—资源—词汇三部图的推荐实现机理;分别进行了用户—资源二部图和资源—词汇二部图中基于能量分配加权的推荐算法实现研究,提出了二部图和能量分配双重加权的三部图推荐实现策略。最后,通过大量的准确性和多样性的实验,验证了所提策略和方法的有效性及优越性。
The realization of social recommendation for user minority needs and long tail resources features plays an important role in improving the quality of network service. According to the mechanism of energy distribution based on mass diffusion and heat spreading in physic kinetics,this paper introduces topics into tripartite to discuss the realization mechanism of recommendation based on user-object-topic tripartite. Then,the paper analyzes the realization of recommendation algorithm based on weighted energy distribution in user-object-topic tripartite and object-topic bipartite and proposes the recommendation strategy of bipartite and doubleweighted energy distribution tripartite. Finally,the paper verifies the effectiveness and superiority of the proposed strategy and method through a large amount of experiments.
The realization of social recommendation for user minority needs and long tail resources features plays an important role in improving the quality of network service. According to the mechanism of energy distribution based on mass diffusion and heat spreading in physic kinetics,this paper introduces topics into tripartite to discuss the realization mechanism of recommendation based on user-object-topic tripartite. Then,the paper analyzes the realization of recommendation algorithm based on weighted energy distribution in user-object-topic tripartite and object-topic bipartite and proposes the recommendation strategy of bipartite and doubleweighted energy distribution tripartite. Finally,the paper verifies the effectiveness and superiority of the proposed strategy and method through a large amount of experiments.
引文
[1]吕琳媛,陆君安,张子柯,等.复杂网络观察[J].复杂系统与复杂性科学,2010(2):173-186.
[2]ZHOU T,et al.Bipartite network projection and personal recommendation[J].Physical Review E,2007,76(4):046115.
[3]GUO Q,LENG R,SHI K,et al.Heat conduction information filtering via local information of bipartite networks[J].European Physical Journal,2012,85(8).DOI:10.1140/epjb/e2012-30095-1.
[4]张新猛,蒋盛益.基于加权二部图的个性化推荐算法[J].计算机应用,2012(3):654-657,678.
[5]胡吉明,张蔓蒂.基于用户—资源关联的社会化小众推荐模型研究[J].情报理论与实践,2014(4):123-126,118.
[6]RAWASHDEH M,KIM H N,ALJA’AM J M,et al.A Folksonomy link prediction based on a tripartite graph for tag recommendation[J].Journal of Intelligent Information Systems,2013,40(2):307-325.
[7]LATHIA N,HAILES S,CAPRA L,et al.Temporal diversity in recommender systems[C]∥Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieva,2010:210-217.
[8]YIN F J,ZHAO X,et al.Improving accuracy and scalability of personal recommendation based on bipartite network projection[J].Mathematical Problems in Engineering,2014:823749.
[9]ZENG W,ZENG A,et al.Similarity from multi-dimensional scaling:solving the accuracy and diversity dilemma in information filtering[J].Plo S one,2014,9(10):e111005.
[10]D el.icio.us[EB/OL].[2014-12-10].http://www.delicious.com.
[11]Movie Lens Data Sets[EB/OL].[2014-12-10].http://www.grouplens.org/node/12.
[12]CLAUSET A,MOORE C,NEWMAN M E J.Hierarchical structure and the prediction of missing links in networks[J].Nature,2008,453(7191):98-101.
[13]ZHANG Z K,ZHOU T,ZHANG Y C.Personalized recommendation via integrated diffusion on user-item-tag tripartite graphs[J].Physica A,2010,389(1):179-186.
[14]ZHANG Z K,LIU C,et al.Solving the cold-start problem in recommender systems with social tags[J].Europhysics Letters,2010,92(2):28002.
[15]ZHAO K,WANG X,YU M,et al.User recommendations in reciprocal and bipartite social networks-an online dating case study[J].IEEE Intelligent Systems,2014,29(2):27-35.
[16]ZHOU T,et al.Solving the apparent diversity-accuracy dilemma of recommender systems[J].Proceedings of the National Academy of Sciences,2010,107(10):4511-4515.
[2]ZHOU T,et al.Bipartite network projection and personal recommendation[J].Physical Review E,2007,76(4):046115.
[3]GUO Q,LENG R,SHI K,et al.Heat conduction information filtering via local information of bipartite networks[J].European Physical Journal,2012,85(8).DOI:10.1140/epjb/e2012-30095-1.
[4]张新猛,蒋盛益.基于加权二部图的个性化推荐算法[J].计算机应用,2012(3):654-657,678.
[5]胡吉明,张蔓蒂.基于用户—资源关联的社会化小众推荐模型研究[J].情报理论与实践,2014(4):123-126,118.
[6]RAWASHDEH M,KIM H N,ALJA’AM J M,et al.A Folksonomy link prediction based on a tripartite graph for tag recommendation[J].Journal of Intelligent Information Systems,2013,40(2):307-325.
[7]LATHIA N,HAILES S,CAPRA L,et al.Temporal diversity in recommender systems[C]∥Proceedings of the 33rd International ACM SIGIR Conference on Research and Development in Information Retrieva,2010:210-217.
[8]YIN F J,ZHAO X,et al.Improving accuracy and scalability of personal recommendation based on bipartite network projection[J].Mathematical Problems in Engineering,2014:823749.
[9]ZENG W,ZENG A,et al.Similarity from multi-dimensional scaling:solving the accuracy and diversity dilemma in information filtering[J].Plo S one,2014,9(10):e111005.
[10]D el.icio.us[EB/OL].[2014-12-10].http://www.delicious.com.
[11]Movie Lens Data Sets[EB/OL].[2014-12-10].http://www.grouplens.org/node/12.
[12]CLAUSET A,MOORE C,NEWMAN M E J.Hierarchical structure and the prediction of missing links in networks[J].Nature,2008,453(7191):98-101.
[13]ZHANG Z K,ZHOU T,ZHANG Y C.Personalized recommendation via integrated diffusion on user-item-tag tripartite graphs[J].Physica A,2010,389(1):179-186.
[14]ZHANG Z K,LIU C,et al.Solving the cold-start problem in recommender systems with social tags[J].Europhysics Letters,2010,92(2):28002.
[15]ZHAO K,WANG X,YU M,et al.User recommendations in reciprocal and bipartite social networks-an online dating case study[J].IEEE Intelligent Systems,2014,29(2):27-35.
[16]ZHOU T,et al.Solving the apparent diversity-accuracy dilemma of recommender systems[J].Proceedings of the National Academy of Sciences,2010,107(10):4511-4515.