基于RoBERTa模型的客户服务热线不满情绪识别系统  

Customer Service Hotline Dissatisfaction Identification System Based on RoBERTa Model

作　　者：赵东明[1] 张继军 ZHAO Dongming;ZHANG Jijun(Artificial Intelligence Laboratory of Tianjin Co.,Ltd.,China Mobile Communications Group,Tianjin 300020,China)

机构地区：[1]中国移动通信集团天津有限公司人工智能实验室,天津300020

出　　处：《天津科技》2023年第8期57-59,63,共4页Tianjin Science & Technology

摘　　要：提出一种基于RoBERTa模型的服务热线潜在不满情绪识别方法,从海量的服务热线语音数据中抽取负面情感信息,并进行潜在不满问题解决。在传统文本情感分析模型基础上通过增加RoBERTa语句向量模块,同时引入注意力(Attention)机制,从而使文本情感分析技术在长篇文本学习中获得更好的效果。该系统在天津移动客户服务工作中体现出了优异的应用效果,显著提升了客户满意度。This paper proposes a method to identify potential dissatisfaction of service hotline based on RoBERTa model,which extracts negative emotional information from massive voice data of service hotline to solve potential dissatisfaction problems.Based on the traditional text sentiment analysis model,by adding the RoBERTa statement vector module,and introducing the attention mechanism,the text sentiment analysis technology can obtain better results in long text learning.The system has demonstrated excellent application effect in the customer service work of Tianjin Mobile and significantly improved the customer satisfaction.

关 键 词：情感计算 文本情绪识别 注意力机制 深度学习 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]