Active help found beneficial in wizard of oz study

https://doi.org/10.1016/S0950-5849(98)00030-5Get rights and content

Abstract

Emerging AI techniques will make possible new intelligent help features, such as ‘active help’ (interrupting the user when appropriate) and ‘back channel’ communication (allowing users to send a message to a help system). An investigation was conducted to determine whether these features would be useful. In the experiment, users of a job scheduling application liked active help and performed better with it than did people without it. However, having a back channel was not particularly valuable to participants. Since developing this feature requires a lot of work, one should find evidence that it will be worth the effort before proceeding.

References (82)

  • R.M. Pilkington

    Questiondashanswering for intelligent ondashline help: The process of intelligent responding

    Cognitive Science

    (1992)
  • E. Rich

    User modeling via sterotypes

    Cognitive Science

    (1979)
  • E. Rich

    Users are individuals: individualizing user models

    International Journal of MandashMachine Studies

    (1983)
  • C.W. Young et al.

    An analysis of ill-formed input in natural language queries to document retrieval systems

    Information Processing and Management

    (1991)
  • R. Amalberti et al.

    User representations of computer systems in humandashcomputer speech interaction

    International J. of MandashMachine Studies

    (1993)
  • J.R. Anderson

    Intelligent tutoring and high school mathematics

  • F. Andry et al.

    Computerised simulation tools for the design of an oral dialogue system

  • M.J. Beeson

    The user model in MATHPERT: an expert system for learning mathematics, artificial intelligence and education

  • D. Benyon et al.

    Applying user modeling to humandashcomputer interaction design

    Artificial Intelligence Review

    (1993)
  • B. Bredeweg et al.

    Student modeling through qualitative reasoning

  • J.A. Breuker et al.

    Model driven knowledge acquisition

  • H. Brunner et al.

    An assessment of written/interactive dialogue for information retrieval applications

    HumandashComputer Interaction

    (1992)
  • A. Burton

    Type in your answer: free text input in computer based learning

    International Journal of Computers in Adult Education and Training

    (1995)
  • R. Catrambone

    Specific versus general procedures in instructions

    Human Computer Interaction

    (1990)
  • D.N. Chin

    Knome: Modeling what the user knows in UC

  • D.N. Chin

    Intelligent interfaces as agents

  • D.N. Chin

    Acquiring user models

    Artificial Intelligence Review

    (1993)
  • A.T. Corbett et al.

    Student modeling and mastery learning in a computer-based programming tutor

  • A.T. Corbett et al.

    Student Modeling and Tutoring Flexibility in the Lisp Intelligent Tutoring System

  • S.J. Derry et al.

    Characterizing the problem solver: a system for ondashline error detection

  • M.C. Desmarais et al.

    User-expertise modeling with empirically derived + — probabilistic implication networks

    User Modeling and User-Adapted Interaction

    (1996)
  • S.M. Doane et al.

    Prompt comprehension in UNIX command production

    Memory & Cognition

    (1992)
  • R. Eberts et al.

    Using neural net modeling for user assistance in HCI tasks

    International Journal of HumandashComputer Interaction

    (1992)
  • T.W. Finin

    GUMS: A general user modeling shell

  • G. Fischer et al.

    Knowledge-based help systems

  • H.P. Greef et al.

    Analysing systemdashuser cooperation in KADS

    Knowledge Acquisition

    (1992)
  • S. Greenberg et al.

    Adaptive personalized interfaces—a question of viability

    Behavior and Information Technology

    (1985)
  • R. Guindon

    Users request help from advisory systems with simple and restricted language: Effects of real-time constraints and limited shared context

    HumandashComputer Interaction

    (1991)
  • M. Hecking

    How to use plan recognition to improve the abilities of the intelligent help system SINIX consultant

  • W.H. Hill

    A Wizard of Oz study of advice giving and following

    HumandashComputer Interaction

    (1993)
  • R.W. Hill et al.

    Situated plan attribution for intelligent tutoring

    • ∗

    Address: Department of Management, P.O. Box 341305, 101 Sirrine Hall, Clemson University, Clemson, South Carolina, 29634-1305, USA. Tel.: 864-656-3768, fax: 864-656-2015.

    View full text
    Copyright © 1998 Published by Elsevier B.V.