Combining a multi-feature neural network with multi-task learning for emergency calls severity prediction

IF 2.3 Q2 COMPUTER SCIENCE, THEORY & METHODS
Array Pub Date : 2023-12-19 DOI:10.1016/j.array.2023.100333
Marianne Abi Kanaan , Jean-François Couchot , Christophe Guyeux , David Laiymani , Talar Atechian , Rony Darazi
{"title":"Combining a multi-feature neural network with multi-task learning for emergency calls severity prediction","authors":"Marianne Abi Kanaan ,&nbsp;Jean-François Couchot ,&nbsp;Christophe Guyeux ,&nbsp;David Laiymani ,&nbsp;Talar Atechian ,&nbsp;Rony Darazi","doi":"10.1016/j.array.2023.100333","DOIUrl":null,"url":null,"abstract":"<div><p>In emergency call centers, operators are required to analyze and prioritize emergency situations prior to any intervention. This allows the team to deploy resources efficiently if needed, and thereby provide the optimal assistance to the victims. The automation of such an analysis remains challenging, given the unpredictable nature of the calls. Therefore, in this study, we describe our attempt in improving an emergency calls processing system’s accuracy in the classification of an emergency’s severity, based on transcriptions of the caller’s speech. Specifically, we first extend the baseline classifier to include additional feature extractors of different modalities of data. These features include detected emotions, time-based features, and the victim’s personal information. Second, we experiment with a multi-task learning approach, in which we attempt to detect the nature of the emergency on the one hand, and improve the severity classification score on the other hand. Additional improvements include the use of a larger dataset and an explainability study of the classifier’s decision-making process. Our best model was able to predict 833 emergency calls’ severity with a 71.27% accuracy, a 5.33% improvement over the baseline model. Moreover, we extended our tool with additional modules that can prove to be useful when handling emergency calls.</p></div>","PeriodicalId":8417,"journal":{"name":"Array","volume":"21 ","pages":"Article 100333"},"PeriodicalIF":2.3000,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2590005623000589/pdfft?md5=2d223cfef124a38eb074b282afcf31c6&pid=1-s2.0-S2590005623000589-main.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Array","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2590005623000589","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, THEORY & METHODS","Score":null,"Total":0}
引用次数: 0

Abstract

In emergency call centers, operators are required to analyze and prioritize emergency situations prior to any intervention. This allows the team to deploy resources efficiently if needed, and thereby provide the optimal assistance to the victims. The automation of such an analysis remains challenging, given the unpredictable nature of the calls. Therefore, in this study, we describe our attempt in improving an emergency calls processing system’s accuracy in the classification of an emergency’s severity, based on transcriptions of the caller’s speech. Specifically, we first extend the baseline classifier to include additional feature extractors of different modalities of data. These features include detected emotions, time-based features, and the victim’s personal information. Second, we experiment with a multi-task learning approach, in which we attempt to detect the nature of the emergency on the one hand, and improve the severity classification score on the other hand. Additional improvements include the use of a larger dataset and an explainability study of the classifier’s decision-making process. Our best model was able to predict 833 emergency calls’ severity with a 71.27% accuracy, a 5.33% improvement over the baseline model. Moreover, we extended our tool with additional modules that can prove to be useful when handling emergency calls.

将多特征神经网络与多任务学习相结合,用于紧急呼叫严重性预测
在紧急呼叫中心,操作员需要在采取任何干预措施之前对紧急情况进行分析并确定优先次序。这样,团队就能在需要时有效地调配资源,从而为受害者提供最佳援助。鉴于呼叫的不可预测性,这种分析的自动化仍具有挑战性。因此,在本研究中,我们将介绍如何根据来电者的语音转录,提高紧急呼叫处理系统对紧急情况严重程度进行分类的准确性。具体来说,我们首先扩展了基线分类器,增加了不同数据模式的特征提取器。这些特征包括检测到的情绪、基于时间的特征和受害者的个人信息。其次,我们尝试使用多任务学习方法,一方面检测紧急情况的性质,另一方面提高严重程度分类得分。其他改进还包括使用更大的数据集以及对分类器决策过程的可解释性研究。我们的最佳模型能够预测 833 个紧急呼叫的严重程度,准确率为 71.27%,比基准模型提高了 5.33%。此外,我们还对工具进行了扩展,增加了在处理紧急呼叫时可能有用的模块。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Array
Array Computer Science-General Computer Science
CiteScore
4.40
自引率
0.00%
发文量
93
审稿时长
45 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信