Meta-Evaluation of Four Intelligent Tutoring Systems: Promises and Products

Abstract

This paper examines two main promises of intelligent tutoring systems (ITS): (1) They will engender more effective and efficient learning in relation to traditional formats, and (2) they will reduce the range of learning outcome scores where a majority of individuals are elevated to high performance levels. Bloom (1984) has referred to these as the 'two sigma problem' - to achieve two standard deviation improvements with tutoring over traditional instruction methods. Four ITS are discussed in relation to the two promises. These tutors have undergone systematic, controlled evaluations: (a) The LISP tutor (Anderson, Farrell, & Sauers, 1984); (b) Smithtown (Shute & Glaser, 1991); (c) Sherlock (Lesgold, Lajoie, Bunzo, & Eggan, 1990); and (d) The PASCAL ITS (Bonar, Cunningham, Beatty, & Weil, 1988). Results show that these four tutors do accelerate learning with no degradation in final outcome. Suggestions for improvements to the design and evaluation of ITS are discussed.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1991
Accession Number
ADA243267

Entities

People

  • Valerie J. Shute

Organizations

  • Armstrong Laboratory

Tags

DTIC Thesaurus Topics

  • Acquisition
  • Air Force
  • Air Force Facilities
  • Cognitive Science
  • Computer Programming
  • Computers
  • Human Resources
  • Instructions
  • Instructors
  • Learning
  • Manpower
  • New York
  • Personnel Management
  • Standards
  • Statistical Analysis
  • Students
  • Test And Evaluation

Readers

  • Artificial Intelligence
  • Military History
  • Systems Analysis and Design