摘要
针对现有基于模型的协同推荐算法推荐精度不高和覆盖面较小的问题,引入社会网络中的信任信息对基于矩阵分解的推荐模型进行扩展,提出一种融合信任传播和矩阵分解的协同推荐算法。首先,基于社会网络中的直接信任关系,提出一种信任传播规则,实现社会网络中信任关系的传递;然后,利用矩阵分解技术降维处理大规模数据集的优势,提出一种融合信任传播机制和矩阵分解模型的协同推荐算法。在Epinions数据集上的实验结果表明,本文提出的推荐算法不仅提高了推荐的精度,而且增加了推荐的覆盖面。
Aiming at the problems that the existing model-based collaborative filtering algorithm has low recommendation accuracy and small recommendation coverage, a collaborative recommendation algorithm integrated trust propagation and matrix factoriza- tion by introducing the trust information of social network to extend the matrix factorization-based recommendation model is pro- posed in this paper. Firstly, a trust propagation rules based on the direct trust relationships of the social network is presented so as to propagate the trust in the social networks. Then a collaborative recommendation algorithm by integrating trust propagation and matrix factorization model is proposed according to the characteristics that the matrix factorization technique can reduce the dimen- sion of large-scale datasets. The experimental results on the Epinions show that the proposed algorithm can not only improve the recommendation accuracy but also increase the recommendation coverage.
出处
《燕山大学学报》
CAS
2013年第5期424-429,共6页
Journal of Yanshan University
基金
河北省自然科学基金资助项目(F2013203124
F2011203219)
河北省高等学校科学技术研究重点项目(ZH2012028)
关键词
协同过滤
社会网络
信任传播
矩阵分解
collaborative filtering
social network
trust propagation
matrix factorization
