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.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1991
- Accession Number
- ADA243267
Entities
People
- Valerie J. Shute
Organizations
- Armstrong Laboratory