面向特定主题的客户抱怨文本分类识别方法  

A method of classifying and identifying customer complaint texts about a particular subject

作　　者：何建民[1] 刘明星[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）》2010年第12期1884-1888,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(70631003;71071047);教育部人文社会科学研究资助项目(10YJA630055)

摘　　要：客户抱怨的自动识别是企业支持和维系客户的关键问题。文章将文本挖掘与支持向量机理论相结合,提出一种网络客户抱怨文本的分类识别方法。该方法通过2次分类识别客户抱怨文本和客户抱怨的类型,主要是通过构建情感词典,选取特征词汇,以特征向量表示客户抱怨文本,以支持向量机的方法分类抱怨文本,并识别抱怨文本类型;用实验方法验证了其合理性和有效性,对企业网上客户抱怨识别和服务质量提高具有重要意义和实用价值。The automatic identification of customer complaints is a critical problem for companies to support and sustain their customers.Based on the combination of text mining with support vector machine（SVM） theory,this paper proposes a method to classify online customer complaint texts.The method identities customer complaint texts and customer complaint types with two steps： firstly,constructing sentiment dictionary to select feature vocabulary;secondly,representing customer complaint texts by feature vectors to classify complaint texts by means of SVM and identifying customer complaint types.Experimental results demonstrate the rationality and validity of the proposed method,which has a significant and practical value for companies to identify online customer complaint and improve the service quality.

关 键 词：客户抱怨 抱怨文本识别 文本挖掘 支持向量机 

分 类 号：N945.12[自然科学总论—系统科学]