高级检索
    李鑫, 刘贵全, 李琳, 吴宗大, 丁君美. LBSN上基于兴趣圈中社会关系挖掘的推荐算法[J]. 计算机研究与发展, 2017, 54(2): 394-404. DOI: 10.7544/issn1000-1239.2017.20150788
    引用本文: 李鑫, 刘贵全, 李琳, 吴宗大, 丁君美. LBSN上基于兴趣圈中社会关系挖掘的推荐算法[J]. 计算机研究与发展, 2017, 54(2): 394-404. DOI: 10.7544/issn1000-1239.2017.20150788
    Li Xin, Liu Guiquan, Li Lin, Wu Zongda, Ding Junmei. Circle-Based and Social Connection Embedded Recommendation in LBSN[J]. Journal of Computer Research and Development, 2017, 54(2): 394-404. DOI: 10.7544/issn1000-1239.2017.20150788
    Citation: Li Xin, Liu Guiquan, Li Lin, Wu Zongda, Ding Junmei. Circle-Based and Social Connection Embedded Recommendation in LBSN[J]. Journal of Computer Research and Development, 2017, 54(2): 394-404. DOI: 10.7544/issn1000-1239.2017.20150788

    LBSN上基于兴趣圈中社会关系挖掘的推荐算法

    Circle-Based and Social Connection Embedded Recommendation in LBSN

    • 摘要: 随着带有GPS定位功能的智能手机越来越普遍,人们喜欢分享他们的地理位置或者通过评论某个地方的商品从而留下用户的足迹,这引发了以共同的兴趣点(POIs)为中心,基于地理位置信息的社交网络研究(location based social network, LBSN).社交网络中的一类典型应用是推荐系统,而推荐系统中最常见的问题是冷启动,即在用户很少点评商家或分享评论时如何为他推荐感兴趣的商家.为解决冷启动问题,提出了一种在社交网络中基于兴趣圈的社会关系挖掘推荐算法.兴趣圈是由所有访问某一类别商品的用户群及他们之间的社会关系构成的社交联系,不同的用户访问同一类别商品表明他们对此类别具有相似兴趣.该方法在传统矩阵分解模型的基础上考虑不同的兴趣圈上的社会关系,使用的社会关系包括朋友关系(显性关系)和相关专家(隐性关系),并用它们作为规则化项来优化矩阵分解模型.实验数据集来自第5届Yelp挑战赛和自己爬取的Foursquare数据集,提出的方法与已有模型进行了充分的实验对比分析,结果表明,我们的模型特别是在解决冷启动问题方面优于多种现有的方法.

       

      Abstract: With the pervasiveness of GPS-enabled smart phones, people tend to share their locations online or check in at somewhere by commenting on the merchants, thus arousing the prevalence of LBSN (location based social network), which takes POIs (point-of-interests) as the center. A typical application in social networks is the recommendation system, and the most common problem in recommendation system is cold start, that is, how to recommend for the users who rarely comment on the item or share comments. In this paper, we propose a recommendation algorithm based on circle and social connections in social networks. The circle is made up by all users who visit a particular category of items and their social connections. It means he is interested in this category that a user accesses the category of items. Our algorithm considers different social connections and circles on tradition matrix factorization. The social connections we use include the relationship between friends(explicit relation) and relevant experts(implicit), which are used as the rule to optimize the matrix factorization model. Experiments are conducted on the datasets from the 5th Yelp Challenge Round and Foursquare. Experimental results demonstrate that our approach outperforms traditional matrix factorization based methods, especially in solving cold-start problem.

       

    /

    返回文章
    返回