考虑社会关系影响差异和动态性的社会化推荐  

Social recommendation based on considerations of different effects and dynamicity of social relations

作　　者：赵海燕[1] 韩松 陈庆奎[1] 曹健[2] Zhao Haiyan;Han Song;Chen Qingku;Cao Jian(Shanghai Key Laboratory of Modern Optical System,School of Optical-Electrical&Computer Engineering,University of Shanghai for Science&Technology,Shanghai 200093,China;Dept.of Computer Science&Technology,Shanghai Jiao Tong University,Shanghai 200030,China)

机构地区：[1]上海理工大学光电信息与计算机工程学院上海现代光学系统重点实验室,上海200093 [2]上海交通大学计算机科学与技术系,上海200030

出　　处：《计算机应用研究》2018年第9期2605-2609,共5页Application Research of Computers

基　　金：国家自然科学基金资助项目(61272438;61202376;61472253);上海市科委资助项目(14511107702);上海市教委科研创新项目(13ZZ112;13YZ075)

摘　　要：随着社交媒体的发展,社交活动日益普及并产生丰富的社会关系。融合社会关系进行推荐可以缓解传统推荐系统面临的数据稀疏和冷启动问题。已有很多成功利用社会关系和评分信息进行推荐的算法,然而它们没有充分地挖掘不同的社会关系对用户的不同影响以及在不同时间段中社会关系的不同影响,这导致推荐效果的下降。基于对现实中社会关系影响复杂性的充分考虑,提出了新的考虑社会关系影响差异和动态性的社会化推荐算法。在Epinions数据集上的实验结果表明该方法可以提高推荐质量。复杂度分析也表明该方法具有可扩展性,能够适应大数据集的要求。With the development of social media,social activities are more and more popular among people and rich social relations have been produced.Fusing social relations to recommend can potentially alleviate data sparse and cold start problems that traditional recommender systems face.Many successful recommendation algorithms employing both social relations and rating information have been proposed in recent years.However,these existing algorithms do not consider much on the differences of the influences generated by each social relation and the temporal changes of social factors,which degraded the performance of recommendation.Based on the fact that the social relations in the real world are very complex,this paper proposed new social recommendation algorithms that considered the different effects and dynamicity of social relations.The experimental results on Epinions dataset show that this method can improve the recommendation quality.The complexity analysis also indicates that this approach can be applied to large datasets.

关 键 词：协同过滤 社交网络 矩阵分解 社交信任 差异性 动态性 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]