| 基于知识的协同过滤推荐系统研究 |
| |
| 引用本文： | 李珊,何建敏,厉浩.基于知识的协同过滤推荐系统研究[J].情报学报,2008,27(3). |
| |
| 作者姓名： | 李珊 何建敏 厉浩 |
| |
| 作者单位： | 1. 东南大学经济管理学院,南京,210096;南京医科大学数学与计算机教研室,南京,2100293;江苏省教育考试院,南京,210024
2. 东南大学经济管理学院,南京,210096 |
| |
| 基金项目： | 国家自然科学基金，江苏省科技型中小企业技术创新基金 |
| |
| 摘 要： | 传统的基于项目的协同过滤算法,不能很好地解决数据稀疏和新项目问题(冷启动)带来的推荐质量下降的问题.笔者从智能检索的思想出发,提出一种新的基于知识的协同过滤推荐算法.该算法借助于领域本体,表达语义知识,增加了项目之间的关联信息;考虑到领域本体中结点、边、深度和密度对相似性计算的不同影响,算法结合信息论中的互信息相关概念,对相似性计算公式进行改进,提高了运算精度.实验结果表明,该算法相对于传统的基于项目的协同过滤推荐算法而言,可有效缓解由数据集稀疏和冷启动带来的问题,显著提高推荐系统的推荐质量.
|
| 关 键 词： | 推荐系统 协同过滤 语义知识 |
Research of Knowledge Based Collaborative Filtering Recommendation Systems |
| |
| Li Shan,He Jianmin,Li Hao.Research of Knowledge Based Collaborative Filtering Recommendation Systems[J].Journal of the China Society for Scientific andTechnical Information,2008,27(3). |
| |
| Authors: | Li Shan He Jianmin Li Hao |
| |
| Institution: | Li Shan He Jianmin Li Hao (1.School of Economics & management,Southeast University,Nanjing 210096,2.Math % Computer Room,Nanjing Medical University,Nanjing 210029,3.Education , Examination Association of Jiangsu,Nanjing 210024) |
| |
| Abstract: | The traditional item-based collaborative fihering(CF)algorithm often suffers from two important problems:sparsity and new iteam(cold star),so the performance of recommendation is low.According to the intelligence information retrieval system,the author presents the new algorithm of collaborative faltering based on knowledge.The semantic knowledge expresses the relation between items and adds useful information.Thinking that the effect of the edge,note,depth and density in ontology is different to simility,t... |
| |
| Keywords: | recommendation system collaborative filtering semantic knowledge |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
