Research on Service Voice Negative Emotion Recognition Method Based on SpanBERT Model

ZHAO Dong-ming; ZHANG Ji-jun; WANG Bo; ZHANG Ya-zhou; LIU Jing; SHI Li

doi:10.3969/j.issn.2096-6091.2023.15.001

您当前的位置：

首页 >

文章列表页 >

Research on Service Voice Negative Emotion Recognition Method Based on SpanBERT Model

RESEARCH PAPER | 更新时间：2025-03-26

- Research on Service Voice Negative Emotion Recognition Method Based on SpanBERT Model
- New Generation of Information Technology Vol. 6, Issue 15, Pages: 1-5(2023)
- 作者机构：
  
  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
  2.天津大学智能与计算学部，天津 300192
- 作者简介：
- 基金信息：
- DOI：10.3969/j.issn.2096-6091.2023.15.001
  CLC： TP391.1
- Accepted：2023-09-20，
  
  Published：15 August 2023
- 稿件说明：
移动端阅览
赵东明, 张继军, 王博, 等. 基于SpanBERT模型的服务语音负面情绪识别方法研究[J]. 新一代信息技术, 2023, 6(15): 01-05

ZHAO Dong-ming, ZHANG Ji-jun, WANG Bo, et al. Research on Service Voice Negative Emotion Recognition Method Based on SpanBERT Model[J]. New Generation of Information Technology, 2023, 6(15): 01-05
赵东明, 张继军, 王博, 等. 基于SpanBERT模型的服务语音负面情绪识别方法研究[J]. 新一代信息技术, 2023, 6(15): 01-05 DOI： 10.3969/j.issn.2096-6091.2023.15.001.

ZHAO Dong-ming, ZHANG Ji-jun, WANG Bo, et al. Research on Service Voice Negative Emotion Recognition Method Based on SpanBERT Model[J]. New Generation of Information Technology, 2023, 6(15): 01-05 DOI： 10.3969/j.issn.2096-6091.2023.15.001.

摘要

方案提出一种基于SpanBERT（Bidirectional Encoder Representations from Transformers by representing and predicting Spans）模型的服务热线文本情感分析方法，以SpanBERT实现句向量优化的文本情感细粒度分析方案，针对移动客服与用户对话数据，实现场景化客服文本分析，通过挖掘负面投诉对话文本价值，并基于识别的客户情绪、语义信息等进行质检，可提前获知客户的潜在不满意倾向，持续提高客户的服务体验，具有很好的推广前景。已应用在天津移动满意度预测、服务运营分析和语音质检工作中，以投诉语音质检机器人替代人工操作，实现降本增效。

Abstract

A service voice negative emotion recognition method based on the SpanBERT (Bidirectional Encoder Representations from Transformers by representing and predicting Spans) model is proposed

which uses SpanBERT to achieve sentence vector optimization for fine-grained text sentiment analysis. Based on conversation data between customer and cervicer

scenario based customer service text analysis is implemented. By mining the value of negative complaint dialogue text and conducting quality inspection based on identified customer emotions

semantic information

etc.

potential dissatisfaction tendencies of customers can be identified in advance

Continuously improving customer service experience has good promotion prospects. It has been applied in China Mobile’s satisfaction prediction

service operation analysis

and voice quality inspection work to complain about voice quality inspection robots

replacing manual operations

and achieving cost reduction and efficiency improvement.

关键词

Keywords

references

汤世松 , 练丽萍 , 贺成龙 , 等 . 一种基于Bert与Bi-LSTM的舆情信息情感识别 [J ] . 网络安全技术与应用 , 2021 , 12 ( 7 ): 31 - 38 .

游兰 , 曾晗 , 韩凡宇 , 等 . 基于BERT-BiGRU集成学习的情感语义识别 [J ] . 计算机技术与发展 , 2023 , 33 ( 5 ): 159 - 166 .

高佳希 , 黄海燕 . 基于TF-IDF多头注意力Transformer模型的文本情感分析 [J ] . 华东理工大学学报(自然科学版) , 2023 , 30 ( 49 ): 68 - 74 .

JOSHI M , CHEN D , LIU Y , et al . SpanBERT: Improving pre-training by representing and predicting spans [J ] . Transactions of the Association for Computational Linguistics , 2020 , 22 ( 8 ): 64 - 77 .

PORTELLI B , DANIELE PASSABÌ , LENZI E , et al . Improving adverse drug event extraction with SpanBERT on different text typologies [J ] . 2021 , 19 ( 11 ): 112 - 124 .

CHEN J , HOEHNDORF R , ELHOSEINY M , et al . Efficient long-distance relation extraction with DG-SpanBERT [J ] . 2020 , 17 ( 22 ): 68 - 77 .

宋泽宇 , 王笑月 , 张虎 , 等 . 基于BERT和题干要素语义增强的高考阅读理解自动答题 [J ] . 计算机应用与软件 , 2023 , 40 ( 7 ): 151 - 158 .

张鑫玉 , 才智杰 . 基于Bert-BiGRU-CNN的文本情感分析 [J ] . 计算机仿真 , 2023 , 40 ( 7 ): 519 - 523 .

李全鑫 , 庞俊 , 朱峰冉 . 结合Bert与超图卷积网络的文本分类模型 [J ] . 计算机工程与应用 , 2023 , 59 ( 17 ): 107 - 115 .

诸林云 , 曲金帅 , 范菁 , 等 . 基于BERT-BiLSTM-Attention的文本情感分析 [J ] . 云南民族大学学报(自然科学版) , 2023 , 32 ( 4 ): 520 - 527,540 .

Views

202

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

No data

Related Author

Zhao DONGMING

Zhang JIJUN

Wang BO

Zhang YAZHOU

Liu JING

Shi LI

Related Institution

Artificial Intelligence Laboratory of China Mobile Communications Group Tianjin Co., Ltd

Intelligence and Computing Department,Tianjin University

⁰