从文本到模型:利用自然语言处理技术开发系统动力学模型

IF 1.7 3区 管理学 Q3 MANAGEMENT
G. A. Veldhuis, Dominique Blok, Maaike H. T. de Boer, G. J. Kalkman, Roos M. Bakker, Rob P.M. van Waas
{"title":"从文本到模型:利用自然语言处理技术开发系统动力学模型","authors":"G. A. Veldhuis, Dominique Blok, Maaike H. T. de Boer, G. J. Kalkman, Roos M. Bakker, Rob P.M. van Waas","doi":"10.1002/sdr.1780","DOIUrl":null,"url":null,"abstract":"Textual data is abundantly available, and natural language processing (NLP) facilitates its analysis. However, system dynamics (SD) modelling relies on the modeller to identify relevant information. We explore the ability of NLP models to support SD modelling by identifying causal sentences in texts. We provide a primer on the notion of causality in SD and on the linguistic properties of causality, followed by an introduction of NLP models suitable for this task. Using three test cases, we evaluate the performance of the NLP models using common evaluation metrics and an SD model completeness metric. We conclude that NLP models can add considerable value to SD modelling, provided that remaining challenges are addressed. One such caveat is the difference we observe between information regarded as causal and information relevant for describing system structure. We discuss how these challenges can be addressed through collaboration between the NLP and SD fields. © 2024 The Author(s). System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.","PeriodicalId":51500,"journal":{"name":"System Dynamics Review","volume":null,"pages":null},"PeriodicalIF":1.7000,"publicationDate":"2024-06-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"From text to model: Leveraging natural language processing for system dynamics model development\",\"authors\":\"G. A. Veldhuis, Dominique Blok, Maaike H. T. de Boer, G. J. Kalkman, Roos M. Bakker, Rob P.M. van Waas\",\"doi\":\"10.1002/sdr.1780\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Textual data is abundantly available, and natural language processing (NLP) facilitates its analysis. However, system dynamics (SD) modelling relies on the modeller to identify relevant information. We explore the ability of NLP models to support SD modelling by identifying causal sentences in texts. We provide a primer on the notion of causality in SD and on the linguistic properties of causality, followed by an introduction of NLP models suitable for this task. Using three test cases, we evaluate the performance of the NLP models using common evaluation metrics and an SD model completeness metric. We conclude that NLP models can add considerable value to SD modelling, provided that remaining challenges are addressed. One such caveat is the difference we observe between information regarded as causal and information relevant for describing system structure. We discuss how these challenges can be addressed through collaboration between the NLP and SD fields. © 2024 The Author(s). System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.\",\"PeriodicalId\":51500,\"journal\":{\"name\":\"System Dynamics Review\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":1.7000,\"publicationDate\":\"2024-06-03\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"System Dynamics Review\",\"FirstCategoryId\":\"91\",\"ListUrlMain\":\"https://doi.org/10.1002/sdr.1780\",\"RegionNum\":3,\"RegionCategory\":\"管理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"MANAGEMENT\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"System Dynamics Review","FirstCategoryId":"91","ListUrlMain":"https://doi.org/10.1002/sdr.1780","RegionNum":3,"RegionCategory":"管理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"MANAGEMENT","Score":null,"Total":0}
引用次数: 0

摘要

文本数据非常丰富,自然语言处理(NLP)为数据分析提供了便利。然而,系统动力学(SD)建模依赖于建模者识别相关信息。我们探讨了 NLP 模型通过识别文本中的因果关系句子来支持 SD 建模的能力。我们首先介绍了 SD 中的因果关系概念和因果关系的语言特性,然后介绍了适合这项任务的 NLP 模型。通过三个测试案例,我们使用常见的评估指标和 SD 模型完整性指标对 NLP 模型的性能进行了评估。我们的结论是,只要能解决剩余的难题,NLP 模型就能为 SD 建模带来相当大的价值。其中一个注意事项是,我们观察到被视为因果关系的信息与描述系统结构的相关信息之间存在差异。我们将讨论如何通过 NLP 和 SD 领域的合作来应对这些挑战。©2024年作者。系统动力学评论》由 John Wiley & Sons Ltd 代表系统动力学学会出版。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
From text to model: Leveraging natural language processing for system dynamics model development
Textual data is abundantly available, and natural language processing (NLP) facilitates its analysis. However, system dynamics (SD) modelling relies on the modeller to identify relevant information. We explore the ability of NLP models to support SD modelling by identifying causal sentences in texts. We provide a primer on the notion of causality in SD and on the linguistic properties of causality, followed by an introduction of NLP models suitable for this task. Using three test cases, we evaluate the performance of the NLP models using common evaluation metrics and an SD model completeness metric. We conclude that NLP models can add considerable value to SD modelling, provided that remaining challenges are addressed. One such caveat is the difference we observe between information regarded as causal and information relevant for describing system structure. We discuss how these challenges can be addressed through collaboration between the NLP and SD fields. © 2024 The Author(s). System Dynamics Review published by John Wiley & Sons Ltd on behalf of System Dynamics Society.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
CiteScore
6.60
自引率
8.30%
发文量
22
期刊介绍: The System Dynamics Review exists to communicate to a wide audience advances in the application of the perspectives and methods of system dynamics to societal, technical, managerial, and environmental problems. The Review publishes: advances in mathematical modelling and computer simulation of dynamic feedback systems; advances in methods of policy analysis based on information feedback and circular causality; generic structures (dynamic feedback systems that support particular widely applicable behavioural insights); system dynamics contributions to theory building in the social and natural sciences; policy studies and debate emphasizing the role of feedback and circular causality in problem behaviour.
×
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