摘要
介绍了如何自动学习用户的喜好和偏好,建立用户模型,然后利用用户模型来优化检索结果的排序。提出了一个基于主题目录的用户模型以及相应的个性化检索排序算法。结果表明,所提出的优化算法能有效地提高Google Di-rectory Search的准确度。
This paper introduces how to automatically learn user interests,build user profiles and re-rank search results.In addition,we propose a topic directory based framework for personalized learning and re-ranking.Experiments are conducted to compare our approach with the popular directory-based search methods（e.g., Google Directory search）.Our experimental results show that the proposed framework can effectively capture personalization and improve the accuracy of personalized search over existing approaches.
出处
《武汉理工大学学报》
CAS
CSCD
北大核心
2010年第16期177-180,共4页
Journal of Wuhan University of Technology
关键词
个性化检索
排序算法
用户模型
主题目录
personalized search
rank algorithm
user profile
topic directory
