摘要
在网络时代,人们之间的交互变得越来越频繁,因而存在于人们交往过程中的信任关系也变得越来越重要,成为多Agent系统和推荐系统中的研究热点之一.信任网络是基于信任的传递性而构建的,从而可以给推荐系统等提供一种有效的信息.由于传统推荐系统存在数据稀疏和冷启动等问题,结合信任的推荐系统应运而生,取得了较好的发展.讨论了信任和信任网络的基础研究,详细介绍了目前信任建模、信任传递等相关方面的研究,分析了目前传统推荐系统的研究和基于信任的推荐系统的研究现状.最后给出了基于信任的推荐系统在未来可能的研究方向.
In Internet age, the interaction between people becomes more and more frequent. Therefore,the trust relationship between people is becoming more and more important. So it has become one of the hot spots in the research on multi-Agent system and recom- mendation system. Trust network is established based on the transitivity of trust,thus it would provide some useful information for rec- ommender systems. Because of the data sparsity and cold-start problems in traditional recommender systems, recommender systems in- tegrated with trust network is proposed. The basic study on trust and trust network is discussed, which includes trust formation, trust transitivity and so on. This paper analyzes the researches on recommender systems and recommender systems based on trust. In addi- tion,the future study directions of recommender systems based on trust are discussed.
出处
《小型微型计算机系统》
CSCD
北大核心
2017年第1期92-98,共7页
Journal of Chinese Computer Systems
基金
国家自然科学基金项目(61572418
61502410
61403329)资助
山东省自然科学基金项目(ZR2013FQ020
ZR2015PF010)资助