期刊文献+

基于社交关系的可信群体推荐

TRUSTED GROUP RECOMMENDATION BASED ON USERS'SOCIAL RELATIONSHIP
下载PDF
导出
摘要 针对当前群体推荐技术只单独考虑用户-项目评分,而没有较好考虑相关上下文信息的问题,提出基于社交关系的可信群体推荐。该方法在相似度计算中考虑群体特性,首先通过两种方式计算单个用户与目标群体之间的可信度,一种是基于距离的社交可信因子,另外一种是基于影响力的社交可信因子;然后将可信因子用于群体与单个用户之间的相似度计算中,使得在后续的群体邻居选取中融入可信度的考虑,从而提升群体邻居的质量,进一步提升推荐的准确度。基于真实数据的仿真实验表明,两种可信度计算方法与已有方法相比在准确性和准确率方面表现更好。 A new trusted group recommendation based on social relationship is proposed to solve the problem of existing technology which considers the user-item rating only but ignores the correlated context information. This new method considers the group characteristics in similarity computation,and first computes the credibility between the single user and the target group in two ways,the one is the distancebased social trusted factor,and the other is the influence-based social trusted factor. Then it applies the trusted factors in computing the similarity between the single user and the target group,this leads to the consideration of credibility being combined in the selection of group neighbours,therefore improves the quality of group neighbours and future improves the accuracy of recommendation. Simulation experiments based on real data indicate that these two credibility computing methods outperform the existing method in both accuracy and precision rate.
作者 幸荔芸
出处 《计算机应用与软件》 CSCD 2015年第12期330-333,共4页 Computer Applications and Software
基金 高职计算机应用技术专业项目情景教学模式的研究(0837034) 高职院校单招生与高考统招生培养质量对比研究(2008-ZJ-045) 酒店管理专业校企合作 工学交替人才培养模式探索(0637393) 基于协商机制的高职院校发展性学生评价的探索与实践(113285)
关键词 群体推荐 社交关系 可信邻居 协同过滤 上下文感知 Group recommendation Social relationship Trusted neighbours Collaborative filtering Context awareness
  • 相关文献

参考文献16

  • 1Bobadilla J,Ortega F,Hernando A,et al.Recommender Systems Survey[J].Knowledge-Based Systems,2013,46(1):109-132.
  • 2Jameson A,Smyth B.Recommendation to Groups[M].The Adaptive Web.Heidelberg:Springer-Verlag Berlin,2007:596-627.
  • 3Dwork C,Kumar R,Navor M,et al.Rank Aggragation Methods for the Web[C]//WWW,New York,2001:613-622.
  • 4Young H P,Levenglick A.A Consistent Extension of Condorcet’s Election Principle[J].SIAM Journal on Applied Mathematics,1978,35(2):285-300.
  • 5Baltrunas L,Makcinskas T,Ricci F.Group Recommendation with Rank Aggregation and Collaborative Filtering[C]//RecS ys,Barcelona,2010:119-136.
  • 6Salamo M,Mccarthy K,Smyth B.Generating Recommendation for Consensus Negotiation in Group Personalization Services[J].Journal Personal and Ubiquitous Computing,2012,16(5):597-610.
  • 7Berkovsky S,Freyne J.Group-based Recipe Recommendations:Analysis of Data Aggregation and Collaborative Filtering[C]//RecS ys,Barcelona,2010:111-118.
  • 8Garcia I,Sebastia L,Onaindia E.On the Design of Individual and Group Recommender Systems for Tourism[J].Expert Systems with Applications,2011,38(6):7683-7692.
  • 9Chirstensen I A,Schiaffino S.Entertainment Recommender Systems for Group of Users[J].Expert Systems with Applications,2011,38:4127-14135.
  • 10Bobadilla J,Ortega F,Hernando A.Generalization of Recommendation Systems:collaborative Filtering Extended to Groups of Users and Restricted to Groups of Items[J].Expert Systems with Applications,2012,39(1):172-186.

二级参考文献8

共引文献297

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部