A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is
Lecture Notes in Computer Science
This paper investigates the effectiveness of conversational agentbased delivery of task strategy and operational help for an interactive search tool. The study tested three modalities of advice (text-only, text-and-audio, and text-audio-and-agent) in addition to a control group with no advice. User-and system-initiated advice modes were also compared. Subjects in the text-only group outperformed other modality groups in usability errors, search performance, advice uptake and in their positivedoi:10.1007/978-3-540-74800-7_38 fatcat:w4o2lrefrzfr7nw4gzzoatszcm