半监督语义动态文本聚类算法  

Semi-Supervised Semantic Dynamic Text Clustering Algorithm

作　　者：钱志森 黄瑞章[1,2] 魏琴[2] 秦永彬[1,2] 陈艳平 QIAN Zhi-sen;HUANG Rui-zhang;WEI Qin;QIN Yong-bin;CHEN Yan-ping(School of Computer Science and Technology,Guizhou University Guiyang 550025;Public Big Data Laboratory of Guizhou,Guizhou University Guiyang 550025)

机构地区：[1]贵州大学计算机科学与技术学院,贵阳550025 [2]贵州大学贵州省公共大数据重点实验室,贵阳550025

出　　处：《电子科技大学学报》2019年第6期803-808,共6页Journal of University of Electronic Science and Technology of China

基　　金：国家自然科学基金联合基金重点项目(U1836205);国家自然科学基金重大研究计划(91746116);黔科合重大专项字([2018]3002);贵州省重大应用基础研究项目(黔科合JZ字[2014]2001);贵州省科技重大专项计划(黔科合重大专项字[2017]3002);贵州省自然科学基金(黔科合基础[2018]1035)

摘　　要：针对传统的动态文本聚类将描述方式不同的同类文本划分到不同组中;以及聚类类别个数与真实类别数之间差距明显等问题,该文提出了一种半监督语义动态文本聚类算法(SDCS).该算法以语义表征文本的方式来捕获文本间的语义关系,在聚类过程中动态学习类别语义,让文本能根据语义准确聚类.同时该算法利用半监督聚类的方法对新类的产生进行监督,学习符合实际情况的聚类结果.实验结果表明该文提出的算法是有效可行的.In the traditional dynamic text clustering, the similar texts with different descriptions are divided into different groups;and the difference between the number of cluster categories and the number of real categories is obvious. Aiming at these problems, this paper proposes a semi-supervised semantic dynamic text clustering algorithm (SDCS). The algorithm captures the semantic relationship between texts by semantically representing the text, and dynamically learns the category semantics during the clustering process, so that the text can be accurately clustered according to semantics. At the same time, the algorithm uses the semi-supervised clustering algorithm to supervise the generation of new classes, and produces clustering results that are consistent with the actual situation. The experimental results show that the proposed algorithm is effective and feasible.

关 键 词：动态文本聚类 语义学习 半监督文本聚类 文本聚类 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]