基于MeSH加权的非相关文献知识发现排序方法研究  

Research on the Disjoint Literature-based Knowledge Discovery Method Based on MeSH Weighting

作　　者：张云秋[1] 于双成[1] 

机构地区：[1]吉林大学公共卫生学院,吉林长春130021

出　　处：《情报理论与实践》2009年第7期113-115,共3页Information Studies:Theory & Application

基　　金：教育部社科研究基金规划项目系列研究成果之一;项目编号:07JA870005

摘　　要：文章在对现有非相关文献知识发现的中间集排序方法进行分析的基础上,以共现理论为基础,以主题关联度为着眼点,提出基于共有MeSH密度加权的B排序方法。并以Swanson的早期发现之一为基础,考察经共有MeSH密度加权与逆文献频率加权两种方法排序筛选后B的范围以及目标关联词和目标关联对的出现情况,以此作为评价其对B影响的依据。结果表明基于共有MeSH加权法能显著提高B的质量,从而提高发现效率。Based on the analysis of the existing ranking method of B collection of disjoint literature-based knowledge discovery, this article proposes a co-MeSH density weighting-based B ranking method according to the cooccurrence theory and the subject relativity, Then, based on one of Swanson＇ s former discoveries, the size of B and the occurrence of target terms and target relations are explored to evaluate their effect on B after ranking and filtering by the co-MeSH density weighting-based method and the inverse document frequency-based weighting method. The results of the experiment indicate the co-MeSH density weighting-based ranking method can improve the quality of B notably and enhance the efficiency of discovery accordingly.

关 键 词：非相关文献 知识发现 主题分析 医学主题词 

分 类 号：G354[文化科学—情报学]