Editor: Nicolas Balacheff, Laboratoire d’informatique de Grenoble
Contributors: Jacqueline Bourdeau, Télé-université, Montréal (Québec)
Paul A. Kirschner, Centre for Learning Sciences and Technologies, Open University of the Netherlands
A cognitive tutor is an intelligent tutoring system which “possesses a computational model capable of solving the problems that are given to students in the ways students are expected to solve the problems" (Anderson et al. 1996 p.3)
Comments on the history
The expression "cognitive tutor" was coined in the context of the Advanced Computer Tutoring Project at Carnegie Mellon University in the mid1980’s. The objective was to design tutors based on "a cognitive model of the competence that the student is being asked to learn" (Anderson et al. p.3). The design of cognitive tutors inherited and is grounded in more than a decade of research on ACT* theory of an architecture of cognition (Anderson 1983). It left the approach based on models informed by human teaching, for models informed by a learning theory so that the environment is able to take actions that facilitate learning because it uses a cognitive model of where the student is in a task (ibid. p.47). Koedinger and Corbett (2006), later with Aleven (2010), experimented innovative methods to produce and evaluate the Cognitive tutors (Koedinger and Corbett p.62). They also provided a research platform for a series of projects on cognitive tutors. Since 2011, Cognitive Tutor™ is a trade mark owned by Carnegie Learning Inc. , the publisher of these tutors (Blessing, 2011).
Intelligent tutoring system, intelligent tutor, tutoring system, model tracing, knowledge tracing, cognitive fidelity, learner model, cognitive science, Cognitive Tutor™
The design of “cognitive tutors” is grounded on the three postulates of the ACT* theory: procedural-declarative distinction, knowledge compilation, strengthening with practice. It complies with the eight following principles (Anderson et al. 1996 pp.14 sqq): (1) represent student competence as a production set, (2) communicate the goal structure underlying the problem-solving, (3) provide instruction in the problem solving context, (4) promote an abstract understanding of the problem-solving knowledge, (5) minimize working memory load, (6) provide immediate feedback on errors, (7) adjust the grain size of instruction with learning, (8) facilitate successive approximations to the target skill. The design of cognitive tutors faces two major challenges (Aleven 2010 p.57): flexibility to adapt to students’ actual solutions, and cognitive fidelity to accurately correspond to the knowledge components students are actually learning. The naming of cognitive tutors too is problematic, since intelligent tutoring systems can be grounded in cognitive science and not be called cognitive tutors.
 Aleven V. (2010) Rule-based cognitive modeling for intelligent tutoring systems. In: Nkambou R., Bourdeau J., Mizoguchi R. (eds.) Advances in Intelligent Tutoring Systems (pp.33-62). Berlin: Springer verlag.
 Anderson J. R. (1983) The Architecture of Cognition. Cambridge, MA: Harvard University Press.
 Anderson J. R., Corbett A. T., Koedinger K. R., Pelletier R. (1996) Cognitive Tutors: Lessons Learned. ARI Research Note 96-66. United States Army, Research Institute for the Behavioral and Social Sciences.
 Blessing, S. (2011) The Cognitive Tutor™: Successful Application of Cognitive Science.
 Koedinger K. & Corbett A. (2006), Cognitive Tutors, in Sawyer, L., Ed., The Cambridge Handbook of the Learning Sciences (pp. 61-77) Cambridge University Press.