The Research and Construction of Complaint Orders Classification Corpus in Mobile Customer Service

摘要：

　　Complaint orders in mobile customer service are the records of complaint description,which professional knowledge and information on customers complaint intention are kept.Complaint orders classification is important and necessary to be established and completed for further mining,analysis and improve the quality of customer service.Constructed corpus is the basis of research.The lack of complaint orders classification corpus(COCC)in mobile customer service has limited the research of complaint orders classification.This paper first employs K-means algorithm and professional knowledge to determine complaint orders classification labels.Then we craft the annotation rules for complaint orders,and then construct complaint orders classification corpus.The corpus consists of 130044 complaint orders annotated.Finally,we statistically analyze the corpus constructed,and the agreement of each question class reaches over 91%.It indicates that the corpus constructed could provide a great support for complaint orders classification and specialized analysis.

关键词： Mobile customer service Complaint orders classification corpus K-means Annotation rules

作者: Junli Xu Jiangjiang Zhao Ning Zhao Chao Xue Linbo Fan Zechuan Qi Qiang Wei

作者单位: IT System Department,China Mobile Online Services Company Limited,Zhengzhou,Henan,China

会议类型: 国际会议

会议名称: 2018自然语言处理与中文计算国际会议(NLPCC2018)

会议地点: 呼和浩特

会议语种:英文

页码: 351-361

在线出版日期: 2018-08-26（万方平台首次上网日期，不代表论文的发表时间）