Interviewer agent for cognitive task analysis

Authors:
Taro Kanno;Masahiro Uetshuhara;Kazuo Furuta
Affiliations:
Bunkyo-ku, Tokyo, Japan;Bunkyo-ku, Tokyo, Japan;Bunkyo-ku, Tokyo, Japan
Venue:
UAHCI'13 Proceedings of the 7th international conference on Universal Access in Human-Computer Interaction: design methods, tools, and interaction techniques for eInclusion - Volume Part I
Year:
2013

Citing 4
Cited 0

Cognitive walkthroughs: a method for theory-based evaluation of user interfaces

International Journal of Man-Machine Studies
ChatterBots, TinyMuds, and the Turing test: entering the Loebner Prize competition

AAAI '94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 1)
ELIZA—a computer program for the study of natural language communication between man and machine

Communications of the ACM
EHeBby: An evocative humorist chat-bot

Mobile Information Systems - Information Assurance and Advanced Human-Computer Interfaces

Quantified Score

Hi-index	0.00

Visualization

Abstract

A chat-based interviewer agent (IA) for cognitive task analysis was developed. This agent automatically generates questions for and responses to the answers from the human interviewee. The automated response process is based on shallow intelligence incorporating an interview technique for cognitive task analysis. We also considered the knowledge awareness (KA) effect and designed the interview as a fake group interview, with one agent interviewer, one agent interviewee, and a human interviewee. We conducted test interviews with 14 subjects to evaluate the new functions of the IA. The results show that KA and the fake group interview were effective and that the performance was better than that of the previous version, which used a one-on-one interview without considering KA.