基于粗糙KNN算法的文本分类方法  

Method of text classification based on rough k-nearest neighbor algorithm

作　　者：王渊[1] 刘业政[1] 姜元春[1] 

机构地区：[1]合肥工业大学管理学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2014年第12期1513-1517,共5页Journal of Hefei University of Technology：Natural Science

基　　金：国家自然科学基金资助项目(71071047)

摘　　要：在文本分类中,数据规模过大或文本分布不均匀对传统KNN算法的准确率和效率具有重要影响。为了解决该问题,文章提出一种基于粗糙KNN(k-nearest neighbor)算法的文本分类新方法。首先引入粗糙集中的上下近似概念定义各类文本的上下近似空间,将文本向量空间分为核心和混合2大区域;然后改进传统KNN算法的隶属度函数;再针对不同的文本区域,采取差异化的分类策略以提高分类的效率和准确率。实验表明,基于粗糙KNN算法的文本分类方法在提高分类准确率的同时,分类的效率也有很大提高。In text classification ,the problems of large‐scale data and imbalanced data distribution affect the accuracy and efficiency of the traditional k‐nearest neighbor（KNN） classification algorithm .To solve the problem ,a new method of text classification based on rough KNN algorithm is presented . Firstly ,the upper approximation space and the lower approximation space are defined by introducing the concepts of upper approximation and lower approximation of rough set theory .Then the vector space of texts is divided into two regions ,namely the core region and the hybrid region .And an improved membership function is put forward .Finally ,the method adopts different classification strategies for different regions .The experimental results show that this method can not only improve the classification accuracy ,but also save largely the classification time .

关 键 词：文本分类 粗糙集 KNN算法 核心区域 混合区域 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]