针对传统协同过滤算法的冷启动、推荐精度低等问题,提出基于用户特征和信任度的推荐算法(Recommendation Algorithm Based on User Characteristics and Trust,RA-UCT).该算法首先利用用户的人口统计学信息和评分数据来计算特征相似度;然后在改进的相似度基础上,构建用户信任网络,计算综合信任度,在特征相似度和综合信任度两个维度上进行推荐.在MovieLens公共数据集上的实验结果表明,与传统协同过滤方法比较,提出的算法能够有效提高推荐精度,冷启动问题也得到有效缓解.
Collaborative Filtering Recommendation Algorithm Based on User Characteristics and Trust
Aiming at the problems of cold boot and low recommendation accuracy of the traditional Collaborative Filtering algorithm,a Recommendation Algorithm Based on User Characteristics and Trust(RA-UCT)is proposed.The algorithm firstly uses the user's demographic information and rating data to calculate the feature similarity.Then,based on the improved similarity,it constructs a user trust network,calculates the comprehensive trust,and makes recommendations based on the two dimensions of feature similarity and comprehensive trust.The experimental results on the MovieLens public dataset show that compared with the traditional Collaborative Filtering method,the proposed algorithm can effectively improve the recommendation accuracy and effectively alleviate the cold boot problem.
国家科技期刊平台
NSTL
万方数据
