基于上下文项目评分分裂的协同过滤推荐  

Collaborative Filtering Recommendation Based on Item Splitting

作　　者：何明[1] 刘毅[1] 常盟盟 吴小飞[1] HE Ming LIU Yi CHANG Meng-meng WU Xiao-fei(College of Computer Science, Beijing University of Technology, Beijing 100124, China)

机构地区：[1]北京工业大学计算机学院,北京100124

出　　处：《计算机科学》2017年第3期247-253,共7页Computer Science

基　　金：国家自然科学基金项目(60803086);国家科技支撑计划子课题(2013BAH21B02-01);北京市自然科学基金项目(4153058;4113076)资助

摘　　要：上下文感知推荐系统的主要任务是利用上下文信息进一步提高推荐系统的推荐精度和用户满意度。提出了一种基于上下文项目评分分裂的推荐方法。该方法首先依据项目分裂判别标准对多维度上下文信息下的项目进行分裂,然后根据分裂结果并通过上下文维度进行聚类。在此基础上,利用协同过滤推荐算法进行未知评分预测。最后,面向不同的项目分裂标准,在LDOS-CoMoDa数据集上进行仿真对比实验。实验结果表明,相对于其他推荐算法,该方法有效提升了推荐精度,达到了提高推荐质量效果的目的。Context-aware recommendation system is an effective way to improve the recommendation accuracy and user satisfaction by using context information. In this paper, an efficient context-item splitting approach for context-aware recommendation was proposed. Firstly, the items are divided according to the item split criterion. Secondly, the cluste- ring is carried out through the context dimension based on the splitting results. Thirdly, the collaborative filtering re- commendation algorithm is used to predict the unknown ratings. Finally, simulation experiments are conducted on the LDOS-CoMoDa data set for different splitting criteria. The experimental results demonstrate that this method can effec- tively improve the accuracy of the recommendation and achieve the goal of improving the quality of recommendation.

关 键 词：上下文感知系统推荐 基于项目的上下文分裂方法 协同过滤 聚类 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]