基于Map Reduce的Bagging贝叶斯文本分类  

Bagging Bayes Text Classification Based on Map Reduce

作　　者：冀素琴[1] 石洪波[1] 卫洁[1] 

机构地区：[1]山西财经大学信息管理学院,太原030031

出　　处：《计算机工程》2012年第16期203-206,211,共5页Computer Engineering

基　　金：国家自然科学基金资助项目(60873100);山西省自然科学基金资助项目(2009011017 4)

摘　　要：集中式系统框架难以进行海量文本数据分类。为此,提出一种基于Map Reduce的Bagging贝叶斯文本分类算法。介绍朴素贝叶斯文本分类算法,将其与Bagging算法结合,运用Map Reduce并行编程模型,在Hadoop平台上实现算法。实验结果表明,该算法分类准确率较高,运行时间较短,适用于大规模文本数据集的分类学习。In order to solve the problem that the classification is difficult on massive text data under the framework of a centralized system, this paper proposes a Bagging Bayes text classification algorithm based on Map Reduce. It introduces the Naive Bayes text classification algorithm. Combined with the Bagging algorithm, it uses Map Reduce parallel programming model to realize the algorithm on Hadoop platform. Experimental results show that this algorithm can be used in the classification of large-scale text data sets, have good accuracy and short running time.

关 键 词：分布式 MAP Reduce模型 文本分类 集成学习 朴素贝叶斯 BAGGING算法 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]