Explanations and Information Foraging in Real-Time Strategy Games

Graduate Thesis Or Dissertation

Analytics

Citeable URL: https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/ms35tf400

Attribute Name	Values
Creator	Penney, Sean J.
Abstract	Assessing and understanding intelligent agents can be a difficult task for users who may lack an artificial intelligence (AI) background. A relatively new area, called “explainable AI,” is emerging to help address this problem, but little is known about how to present and structure information that an explanation system might offer. To inform the development of explainable AI systems, we analyzed the “supply” of explanations that experts provided in the real-time strategy domain and conducted an information foraging theory based study to determine if these explanations meet the “demand” of experienced users. Our results showed some consistency between explanations experts offer and what system users demand. We also found foraging problems, however, that caused participants to entirely miss important events and reluctantly ignore other actions, resulting in high cognitive, navigation, and information costs to access the information they needed.
License	All rights reserved
Resource Type	Masters Thesis
Date Issued	2017-11-28
Degree Level	Master's
Degree Name	Master of Science (M.S.)
Degree Field	Computer Science
Degree Grantor	Oregon State University
Commencement Year	2018
Advisor	Burnett, Margaret M.
Committee Member	Sarma, Anita Parrish, Christopher Scaffidi, Christopher
Academic Affiliation	Electrical Engineering and Computer Science
Subject	HCI
Rights Statement	In Copyright
Publisher	Oregon State University
Language	English [eng]

Parents:

This work has no parents.

In Collection:

Thumbnail	Title	Date Uploaded	Visibility	Actions
	PenneySeanJ2017v2.pdf	2017-12-18	Public	Download