现有的推荐系统研究大都千方百计地关注于如何提高推荐算法的准确性,考虑到用户兴趣的覆盖范围,这样做的缺陷是只考虑了推荐列表中单个项目的准确度,而忽略了整个推荐列表多样性对用户满意度的影响。近几年的研究表明将信任机制融入到个性化推荐过程中对提高传统协同过滤技术的准确性和鲁棒性有积极的影响,本文提出了基于社会网络信任的推荐多样性算法,该算法通过选择主题多样性好的信任邻居来平衡推荐结果的准确性和多样性。一系列的实验结果表明,该算法能有效地提高推荐的多样性。
Considering users' complete spectrum of interests, the limitation of current research on recommender systems lies in that they only pay attention to improving the accuracy of recommendation algorithm while neglect recommendation diversification. Recent research has shown that incorporating trust and reputation models into the recommendation process can have a positive impact on the accuracy and robustness of collaborative filtering. This paper proposes a novel recommendation diversification algorithm for trust based E-commerce personalized recommender systems, which is designed to balance the accuracy and the diversification of the recommendation list. A series of experiments show that the algorithm can improve the recommendation diversification.