arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2311.02102cs.AI

可解释人工智能的概念——一项来自用户视角的实证研究

Notion of Explainable Artificial Intelligence -- An Empirical Investigation from A Users Perspective

LUT University(拉普兰塔理工大学);Norwegian University of Science and Technology(挪威科技大学)

AKM Bahalul Haque, A. K. M. Najmul Islam, Patrick Mikalef

AI总结:

本研究以推荐系统为场景,通过焦点小组访谈探究用户视角的可解释AI需求,发现用户需要非技术、定制化且可靠的解释及数据使用说明,进而提出让用户参与开发流程的整合框架。

摘要:

基于人工智能的应用受到的关注度日益提升,这引发了学界对可解释性问题的研究兴趣。目前针对可解释人工智能(XAI)的新兴研究热潮表明,有必要开展以终端用户为中心的可解释人工智能研究。为此,本研究以推荐系统为研究场景,旨在探究以用户为中心的可解释人工智能。我们开展了焦点小组访谈,收集关于推荐系统的定性数据。我们向参与者询问了终端用户对推荐条目的理解情况、推荐条目可能的解释方式,以及他们对让推荐具备可解释性的看法。研究结果显示,终端用户需要非技术性、量身定制的解释,同时支持按需提供补充信息。此外,我们还发现用户要求对个人数据使用情况作出解释、提供详细的用户反馈,以及真实可靠的解释。最后,我们提出了一个整合框架,旨在让终端用户参与到开发流程中,参与需求收集与验证工作。

英文摘要:

The growing attention to artificial intelligence-based applications has led to research interest in explainability issues. This emerging research attention on explainable AI (XAI) advocates the need to investigate end user-centric explainable AI. Thus, this study aims to investigate usercentric explainable AI and considered recommendation systems as the study context. We conducted focus group interviews to collect qualitative data on the recommendation system. We asked participants about the end users' comprehension of a recommended item, its probable explanation, and their opinion of making a recommendation explainable. Our findings reveal that end users want a non-technical and tailor-made explanation with on-demand supplementary information. Moreover, we also observed users requiring an explanation about personal data usage, detailed user feedback, and authentic and reliable explanations. Finally, we propose a synthesized framework that aims at involving the end user in the development process for requirements collection and validation.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑