Capturing the Trends, Applications, Issues, and Potential Strategies of Designing Transparent AI Agents

Lingyun Sun, Zhuoshu Li, Yuyang Zhang, Yanzhen Liu, Shanghua Lou, Zhibin Zhou

Research output: Chapter in book / Conference proceedingConference article published in proceeding or bookAcademic researchpeer-review

2 Citations (Scopus)

Abstract

With the increasing prevalence of Artificial Intelligence (AI) agents, the transparency of agents becomes vital in addressing the interaction issues (e.g., explainability and trust). The existing body of research provides valuable theoretical and practical studies in this field. However, determining the transparency of AI agents requires the systematic consideration of the application categories and automation level, which is hardly considered by the prior literature. We thus apply the bibliometric analysis to gain insights from the published literature. Our work outlines the trend of how the number of studies about AI agent transparency increased over the years. We also identify the major application topics and issues in designing transparent AI agents. Furthermore, we categorize the identified applications according to the specific dimensions (risk and timeliness) and put forward potential strategies for designing different agents. Besides, we suggest the possible transparency degree corresponding to the automation level.

Original languageEnglish
Title of host publicationExtended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems, CHI EA 2021
PublisherAssociation for Computing Machinery
ISBN (Electronic)9781450380959
DOIs
Publication statusPublished - 8 May 2021
Externally publishedYes
Event2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI EA 2021 - Virtual, Online, Japan
Duration: 8 May 202113 May 2021

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

Conference2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI EA 2021
Country/TerritoryJapan
CityVirtual, Online
Period8/05/2113/05/21

Keywords

  • AI
  • Transparency
  • Transparent agent
  • Trend

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Fingerprint

Dive into the research topics of 'Capturing the Trends, Applications, Issues, and Potential Strategies of Designing Transparent AI Agents'. Together they form a unique fingerprint.

Cite this