基于TF-IDF算法的运营商客户投诉原因研究  

Reasons for Customer Complaints in Operators Based on TF-IDF Algorithm

作　　者：张爱华[1] 孙嘉鸿 ZHANG Aihua;SUN Jiahong(School of Economics and Management,Beijing University of Posts and Telecommunications,Beijing 100876,China)

机构地区：[1]北京邮电大学经济管理学院,北京100876

出　　处：《北京邮电大学学报（社会科学版）》2024年第2期39-49,共11页Journal of Beijing University of Posts and Telecommunications(Social Sciences Edition)

基　　金：通鼎研究基金。

摘　　要：针对运营商人工处理客户投诉工单高成本低效率问题,提出了一种基于TF-IDF算法的定量研究方法,旨在高效精准地识别客户投诉原因。选用Jieba分词,导入自定义词典和停用词列表,对运营商客户投诉工单进行关键词抽取,获取各类问题中TF-IDF值排名前6的关键词,输出关键词集。提高了关键词抽取的准确性和效率。此外,对比仅对文档集使用TF进行统计和使用TextRank算法的情况,突显了IDF的重要性及算法原理的差异。实验结果表明,光猫、路由器、机顶盒问题广泛存在于各类投诉中。针对这三类问题,为运营商提供了改进产品、服务的相关建议,对运营商集中治理、解决问题具有一定的实用价值。Focusing on the issue of high cost and low efficiency associated with manual processing of customercomplaints by operators, a quantitative research method based on TF-IDF (term frequency-inverse documentfrequency) algorithm is proposed, aiming to efficiently and accurately identify the reasons for customercomplaints. Jieba, combined with the custom dictionary and the list of stopword is used to extract key words fromcomplaint worksheets. The top six key words with the highest TF-IDF values in each issue are obtained, and aset of key words is output, thereby enhancing the accuracy and efficiency of keyword extraction. Furthermore, bycomparing this method with the sole use of TF and the application of the TextRank algorithm, the importance ofIDF and the differences in algorithmic principles are highlighted. Results indicate that issues related to opticalmodems, routers, and set-top boxes widely exist in complaints. In terms of these issues, this study providesoperators with relevant suggestions for improving products and services, which have certain value to operators’managing and solving problems.

关 键 词：投诉工单 投诉原因 关键词抽取 TF-IDF 

分 类 号：F626.5[经济管理—产业经济]