基于混合相似度和用户兴趣迁移的改进协同过滤推荐算法  

Improved collaborative filtering recommendation algorithm based on hybrid similarity and user interest transfer

作　　者：夏翔 刘姜[1] 倪枫[1] 肖云天 Xia Xiang;Liu Jiang;Ni Feng;Xiao Yuntian(Business School,University of Shanghai for Science and Technology,Shanghai 200093,China)

机构地区：[1]上海理工大学管理学院,上海200093

出　　处：《计算机时代》2023年第3期36-39,共4页Computer Era

基　　金：国家自然科学基金(11701370);上海市“系统科学”高峰学科建设项目。

摘　　要：HSIT-CF算法利用熵权法计算出各个用户属性类型权重,构造出用户属性相似度,同时利用项目及评价的时间信息作为权重因子描述用户兴趣迁移,从而提出改进后的用户评分预测公式。实验表明,该算法降低了预测误差,在计算相似度时更加准确,提高了推荐质量。The HSIT-CF algorithm uses the entropy weight method to calculate the weight of each user attribute type, constructs the similarity of user attributes, and uses items and time information of evaluations as weight factors to describe the user interest migration, so as to propose an improved user rating prediction formula. Experiments show that the algorithm reduces the prediction error, is more accurate in calculating the similarity, and improves the recommendation quality.

关 键 词：协同过滤 属性相似度 用户兴趣 时间权重 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]