基于受控词表的医学资源社会化标签推荐研究  

Study on Social Tagging Recommendation Model Based on Controlled Thesaurus in Medical Resources

作　　者：贾君枝[1] 孙智超[1] 邰杨芳[2] 

机构地区：[1]山西大学经济与管理学院,太原030006 [2]山西医科大学,太原030012

出　　处：《情报学报》2013年第12期1326-1332,共7页Journal of the China Society for Scientific and Technical Information

基　　金：国家社科基金项目“叙词表与分众分类系统的集成研究”(项目编号:11BTQ006);山西省高等学校青年学术带头人项目“分众分类法与受控词表的集成方法研究”(项目编号:1005730)研究成果之一

摘　　要：社会化标注是Web2．0环境下的新兴标注方法，标签是其核心要素，但是标签的多样性、模糊性、非结构化以及语义关系不明等特点影响着信息检索的效率。本文以“豆丁医学”为例，利用《中国分类主题词表》的层级结构关系和标签的统计学规律，建立标签和主题词间的映射关系。并通过标签聚类来扩展这种映射，为用户提供更好地标签推荐和层次浏览机制。实验证明，本文提出的基于主题词的标签推荐模型能够较好地为用户提供标签推荐和分类导航服务。Social tagging is a new annotation method under Web2.0 environment and tag is the core element in it; however its diversity, ambiguity, unstructured and unknown semantic characteristics affect the efficiency of information retrieval. This paper takes ＂ Douding medicine＂ as an example, uses the hierarchy relations of Classified Chinese Thesaurus and statistical regularity of tags to establish the mapping relationship between tags and thesaurus. Tag clustering extends this mapping, to provide users with a better tag recommendations and level browsing mechanism. Tests prove that the model based on the thesaurus of social tagging recommended model be better able to provide tag recommendation and classified navigation services for users.

关 键 词：社会化标注 标签 映射 标签推荐 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]