论文部分内容阅读
为了解决推荐中存在的数据稀疏、准确度不高等问题,提出了一种基于用户信任网络的推荐方法.首先利用基本的社会网络,融合用户的基本信任关系、角色影响力、属性相似关系、偏好相似关系构造带权重的社会网络;然后基于此网络提出关键路径发现算法以发现满足约束条件的用户信任网络;最后基于用户信任网络进行推荐.在Filmtipset数据集上对影响推荐质量的各个因素进行了对比分析,结果表明,基于用户信任网络的方法能得到更好的推荐效果.
In order to solve the problem that the data in the recommendation is sparse and the accuracy is not high, this paper proposes a recommendation method based on the user trust network.First, the basic social network is used to integrate the user’s basic trust relationship, role influence, attribute similarity, preference Then constructs the key path discovery algorithm based on this network to find the user trust network that satisfies the constraint condition and finally makes recommendations based on the user trust network.All the factors influencing the quality of recommendation on the Filmtipset dataset The comparative analysis shows that the method based on user trust network can get better recommendation results.