Toward foraging for understanding of StarCraft agents: An empirical study

Sean Penney, Jonathan Dodge, Claudia Hilderbrand, Andrew Anderson, Logan Simpson, Margaret Burnett

Research output: Chapter in Book/Report/Conference proceedingConference contribution

25 Scopus citations

Abstract

Assessing and understanding intelligent agents is a difficult task for users that lack an AI background. A relatively new area, called "Explainable AI," is emerging to help address this problem, but little is known about how users would forage through information an explanation system might offer. To inform the development of Explainable AI systems, we conducted a formative study - using the lens of Information Foraging Theory - into how experienced users foraged in the domain of StarCraft to assess an agent. Our results showed that participants faced difficult foraging problems. These foraging problems caused participants to entirely miss events that were important to them, reluctantiy choose to ignore actions they did not want to ignore, and bear high cognitive, navigation, and information costs to access the information they needed.

Original languageEnglish (US)
Title of host publicationIUI 2018 - Proceedings of the 23rd International Conference on Intelligent User Interfaces
PublisherAssociation for Computing Machinery
Pages225-237
Number of pages13
ISBN (Electronic)9781450349451
DOIs
StatePublished - Mar 5 2018
Event23rd ACM International Conference on Intelligent User Interfaces, IUI 2018 - Tokyo, Japan
Duration: Mar 7 2018Mar 11 2018

Publication series

NameInternational Conference on Intelligent User Interfaces, Proceedings IUI

Conference

Conference23rd ACM International Conference on Intelligent User Interfaces, IUI 2018
Country/TerritoryJapan
CityTokyo
Period3/7/183/11/18

All Science Journal Classification (ASJC) codes

  • Software
  • Human-Computer Interaction

Fingerprint

Dive into the research topics of 'Toward foraging for understanding of StarCraft agents: An empirical study'. Together they form a unique fingerprint.

Cite this