中文文本主题聚类算法研究综述  

Summary of Research on Chinese Text Topic Clustering Algorithms

作　　者：徐菲菲 陈赛红 XU Feifei;CHEN Saihong(School of Computer Science and Technology,Shanghai University of Electric Power,Shanghai 200090,China)

机构地区：[1]上海电力大学计算机科学与技术学院,上海200090

出　　处：《上海电力大学学报》2021年第6期613-619,共7页Journal of Shanghai University of Electric Power

基　　金：国家自然科学基金(61272437,61305094);上海市教育发展基金会和上海市教育委员会“晨光计划”(13CG58)。

摘　　要：相对于传统的纸媒体,网络媒体中的数据具有更新速度快、用户参与度高、覆盖面广等特点。如何协助用户在较短时间了解网络媒体中的主题信息,是一个亟待研究的领域。目前,文本主题聚类的研究技术还不够成熟,且在国内处于不断研究的阶段,尤其是在中文文本领域。对国内外主题检测研究现状、主题挖掘基本步骤、聚类算法的优缺点等方面进行了系统的概述,指出了当前研究方法的不足以及未来可研究的方向。Compared with traditional print media,the data in network media has the characteristics of fast update speed,high user participation,and wide coverage.How to help users quickly understand the subject information in online media is an area that needs urgent research.At present,research technology is not mature enough in this area,which is at a constantly exploring stage in China.Therefore,a systematic overview of the current status of domestic and international research on topic detection,the basic steps of topic mining,and the advantages and disadvantages of clustering algorithms is provided.The deficiency of current research methods and future research interests are pointed out.

关 键 词：聚类 中文文本 主题检测 主题挖掘 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]