基于Porter算法的英文标签聚类方法研究  

An English Tag Clustering Method Based on the Porter Stemming Algorithm

作　　者：窦永香[1] 苏山佳[1] 赵捧未[1] 

机构地区：[1]西安电子科技大学经济管理学院,西安710071

出　　处：《现代图书情报技术》2009年第9期40-44,共5页New Technology of Library and Information Service

基　　金：国家自然科学基金项目“基于语义对等网的知识组织和灵捷检索研究”(项目编号:70873090)的研究成果之一

摘　　要：针对大众标注中用户添加标签具有随意性且不受系统控制的问题,引入著名的Porter算法对英文标签进行词根提取,在此基础上提出可以根据用户需要进行精度选择的英文标签聚类算法,并利用标签云进行模拟实验。实验表明,采用此聚类算法有利于根据用户的需要组织标签并更准确地描述资源。The tags added by users are free rein and uncontrolled in folksonomy systems, so the porter stemming algorithm is introduced firstly in this paper to extract the roots of English tags. Then the method of clustering English tags is brought forward, which chooses the precision following the user＇ s choice. Finally, making use of the tag cloud, simulation experiment is conducted and proves that this algorithm can make the English tags clustered according to the user＇ s requirement and describe the resource better.

关 键 词：大众标注 标签 聚类 

分 类 号：G354[文化科学—情报学]