以用户为中心的可解释人工智能(XAI)评估:系统性文献综述

IF 4.3 Q1 PSYCHOLOGY, MULTIDISCIPLINARY
Noor Al-Ansari, Dena Al-Thani, Reem S. Al-Mansoori
{"title":"以用户为中心的可解释人工智能(XAI)评估:系统性文献综述","authors":"Noor Al-Ansari,&nbsp;Dena Al-Thani,&nbsp;Reem S. Al-Mansoori","doi":"10.1155/2024/4628855","DOIUrl":null,"url":null,"abstract":"<p>Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full-text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user-centered studies in the field of XAI.</p>","PeriodicalId":36408,"journal":{"name":"Human Behavior and Emerging Technologies","volume":null,"pages":null},"PeriodicalIF":4.3000,"publicationDate":"2024-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/4628855","citationCount":"0","resultStr":"{\"title\":\"User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review\",\"authors\":\"Noor Al-Ansari,&nbsp;Dena Al-Thani,&nbsp;Reem S. Al-Mansoori\",\"doi\":\"10.1155/2024/4628855\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p>Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full-text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user-centered studies in the field of XAI.</p>\",\"PeriodicalId\":36408,\"journal\":{\"name\":\"Human Behavior and Emerging Technologies\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.3000,\"publicationDate\":\"2024-07-15\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"https://onlinelibrary.wiley.com/doi/epdf/10.1155/2024/4628855\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Human Behavior and Emerging Technologies\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://onlinelibrary.wiley.com/doi/10.1155/2024/4628855\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"PSYCHOLOGY, MULTIDISCIPLINARY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Human Behavior and Emerging Technologies","FirstCategoryId":"1085","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/2024/4628855","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"PSYCHOLOGY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0

摘要

研究人员开发了多种方法,利用以用户为中心的人机交互(HCI)技术来评估可解释人工智能(XAI)系统。本系统性文献综述旨在了解这些方法如何用于实现 XAI 目标。本综述旨在探讨在涉及人类受试者的研究中用于评估 XAI 系统的方法。从 2018 年至 2023 年期间从四个知名数据库获得的 3414 项研究样本中,系统地选择和分析了共计 101 项全文研究。分析的重点是在 10 个领域实现的突出 XAI 目标,以及用于创建这些 XAI 系统的机器学习(ML)模型。分析还探讨了研究人员在以往工作中使用的解释方法和详细研究方法。分析最后将研究人员遇到的挑战分为三类。在探讨研究人员采用的方法时,综述讨论了数据收集方法和参与者招募的优点和缺点。最后,本综述提供了一个由六大支柱组成的框架,研究人员在评估 XAI 领域以用户为中心的研究时可加以遵循。
本文章由计算机程序翻译,如有差异,请以英文原文为准。

User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review

User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review

Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full-text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user-centered studies in the field of XAI.

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
Human Behavior and Emerging Technologies
Human Behavior and Emerging Technologies Social Sciences-Social Sciences (all)
CiteScore
17.20
自引率
8.70%
发文量
73
期刊介绍: Human Behavior and Emerging Technologies is an interdisciplinary journal dedicated to publishing high-impact research that enhances understanding of the complex interactions between diverse human behavior and emerging digital technologies.
×
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