Cognitive Computer Tutors: Solving the Two-Sigma Problem
Individual human tutoring is the most effective and most expensive form of instruction. Students working with individual human tutors reach achievement levels as much as two standard deviations higher than students in conventional instruction (that is, 50% of tutored students score higher than 98% of the comparison group). Two early 20th-century innovations attempted to offer benefits of individualized instruction on a broader basis: (1) mechanized individualized feedback (via teaching machines and computers) and (2) mastery learning (individualized pacing of instruction). On average each of these innovations yields about a half standard deviation achievement effect. More recently, cognitive computer tutors have implemented these innovations in the context of a cognitive model of problem solving. This paper examines the achievement effect size of these two types of student-adapted instruction in a cognitive programming tutor. Results suggest that cognitive tutors have closed the gap with and arguably surpass human tutors.
KeywordsStandard Deviation Intelligent Tutoring System Teaching Machine Model Trace Instructional Time
Unable to display preview. Download preview PDF.
- 1.Bloom, B.S.: The 2_Sigma Problem: The search for methods of group instruction as effective as one-to-one tutoring. Educational Researcher 13 (1984) 3–15Google Scholar
- 3.Pressey, S.L.: A simple apparatus which gives tests and scores-and teaches. School and Society 23 (1926) 373–376Google Scholar
- 4.Kulik, J.A.: Meta-analytic studies of findings on computer-based instruction. In E. Baker & H. O’Neil (Eds.) Technology assessment in education and training. Lawrence Erlbaum, Mahwah, NJ (1994) 9–33Google Scholar
- 7.Liao, Y.: Effects of computer-assisted instruction on cognitive outcomes: A metaanalysis. Journ al of Research on Computing in Education 24 (1992) 367–380Google Scholar
- 8.Niemiec, R., Walberg, H.J.: Comparative effectiveness of computer-assisted instruction: A synthesis of reviews. Journal of Educational Computing Research 3 (1987) 19–37Google Scholar
- 9.Bloom, B.S.: Learning for mastery. In Evaluation Comment, 1. UCLA Center for the Study of Evaluation of Instructional Programs, Los Angeles, CA (1968)Google Scholar
- 13.Corbett, A.T., Anderson, J.R.: Locus of feedback control in computer-based tutoring: Impact on learning rate, achievement and attitudes. Proceedings of ACTM CHI’2001 Conference on Human Factors in Computing Systems (in press)Google Scholar
- 14.Corbett, A.T., Anderson, J.R.: Knowledge decomposition and subgoal reification in the ACT Programming Tutor. Artificial Intelligence and Education, 1995: The Proceedings of AI-ED 95. AACE., Charlottesville, VA (1995) 469–476Google Scholar
- 15.Corbett, A.T., Knapp, S.: Plan scaffolding: Impact on the process and product of learning. In C. Frasson, G. Gauthier, & A. Lesgold (Eds.) Intelligent tutoring systems: Third international conference, ITS’ 96. Springer, New York (1996) 120–129Google Scholar
- 16.Corbett, A.T., Bhatnagar, A.: Student modeling in the ACT Programming Tutor: Adjusting a procedural learning model with declarative knowledge. User Modeling: Proceedings of the Sixth International Conference, UM97. Springer, New York, (1997) 243–254Google Scholar
- 18.Anderson, J.R., Gluck, K.: What role do cognitive architectures play in intelligent tutoring systems. In D. Klahr & S. Carver (Eds.) Cognition and instruction: 25 years of progress. Lawrence Erlbaum, Mahwah, NJ (in press)Google Scholar
- 19.Aleven, V., Koedinger, K.R.: Toward a tutorial dialog system that helps students to explain solution steps. Building Dialogue Systems for Tutorial Applications: AAAI Fall Symposium 2000, (2000)Google Scholar