Keywords

mouse cursor tracking, uncertainty, area-under-the-curve, adaptive computers

Abstract

Providing information online is pervasive in human-computer interactions. While providing information, people may deliberate their responses. However, organizations only receive the end-result of this deliberation and therefore have no contextual information surrounding the response. One type of contextual information includes knowing people’s response uncertainty while providing information. Knowing uncertainty allows organizations to weigh responses, ask follow-up questions, provide assistance, or identify problematic instructions or responses. This paper explores how mouse cursor movements may indicate uncertainty in a human-computer interaction context. Specifically, it hypothesizes how uncertainty on multiple-choice questions influences a mouse-movement statistic called area-under-the-curve (AUC). We report the result of two studies that suggest that AUC is higher when people have moderate uncertainty about an answer than if people have high or low uncertainty. The results suggest a methodology for measuring uncertainty to facilitate multi-method research and to assess data in a pragmatic setting.

Original Publication Citation

Jenkins, J. L., Larsen, R., Valacich, J. S., Bodily, R., Sandberg, D., Williams, P., Stokes, S., Harris, S. (2015) "A Multi-Experimental Examination of Analyzing Mouse Cursor Trajectories to Gauge Subject Uncertainty", Americas Conference on Information Systems, Puerto Rico, August 13-15. Best Paper Nominee

Document Type

Conference Paper

Publication Date

2015

Publisher

Americas Conference on Information Systems

Language

English

College

Marriott School of Business

Department

Information Systems Management

University Standing at Time of Publication

Full Professor

Download

Share

COinS