Cognitive Tutor Research Articles

An effective metacognitive strategy: learning by doing and explaining with a computer‐based Cognitive Tutor

AbstractRecent studies have shown that self‐explanation is an effective metacognitive strategy, but how can it be leveraged to improve students' learning in actual classrooms? How do instructional treatments that emphasizes self‐explanation affect students' learning, as compared to other instructional treatments? We investigated whether self‐explanation can be scaffolded effectively in a classroom environment using a Cognitive Tutor, which is intelligent instructional software that supports guided learning by doing. In two classroom experiments, we found that students who explained their steps during problem‐solving practice with a Cognitive Tutor learned with greater understanding compared to students who did not explain steps. The explainers better explained their solutions steps and were more successful on transfer problems. We interpret these results as follows: By engaging in explanation, students acquired better‐integrated visual and verbal declarative knowledge and acquired less shallow procedural knowledge. The research demonstrates that the benefits of self‐explanation can be achieved in a relatively simple computer‐based approach that scales well for classroom use.

Modeling Student Knowledge: Cognitive Tutors in High School and College

This paper examines the role of adaptive student modeling in cognitive tutor research and dissemination. Cognitive tutorsTM are problem solving environments constructed around cognitive models of the knowledge students are acquiring. Over the past decade we in the Pittsburgh Advanced Cognitive Tutor (PACT) Center at Carnegie Mellon have been employing a cognitive programming tutor in university-based teaching and research, while simultaneously developing cognitive mathematics tutors that are currently in use in about 150 schools in 14 states. This paper examines adaptive student modeling issues in these two contexts. We examine the role of student modeling in making the transition from the research lab to widespread classroom use, describe our university-based efforts to empirically validate student modeling in the ACT Programming Tutor, and conclude with a description of the key role that student modeling plays in formative evaluations of the Cognitive Algebra II Tutor.

The use of a cognitive tutoring system in the improvement of the abstract reasoning component of word problem solving

This study evaluated the Word Problem Solving (WPS) Tutor's ability to improve the abstract reasoning component of word problem solving. Six hundred and thirty-two ninth grade students were assigned to three groups: a control group exposed to traditional group instruction, a placebo group exposed to traditional group instruction plus a computerized word problem solving environment with no active tutoring, and an experimental group exposed to traditional group instruction and a computerized word problem solving environment with active tutoring. A paper and pencil test was administered to students at the beginning of the school year, at mid-term, and at the end of the school year and was used to compare the performance of the three groups on the concrete and abstract components of word problem solving. Results indicated that WPS-Tutored students improved significantly more than either the control group or the placebo group on both the abstract and concrete reasoning subtests. However, performance gains on the abstract subtest were not as large as the gains on the concrete subtest. Implications for math education and suggestions for future research and development efforts are discussed.

Illustrating Principled Design: The Early Evolution of a Cognitive Tutor for Algebra Symbolization

(1998). Illustrating Principled Design: The Early Evolution of a Cognitive Tutor for Algebra Symbolization. Interactive Learning Environments: Vol. 5, No. 1, pp. 161-179.

Cognitive Tutors: Lessons Learned

This paper review the 10-year history of tutor development based on the ACT theory (Anderson, 1983,1993). We developed production system models in ACT ofhow students solved problems in LISP, geometry, and algebra. Computer tutors were developed around these cognitive models. Construction ofthese tutors was guided by a set of eight principles loosely based on the ACT theory. Early evaluations of these tutors usually but not always showed significant achievement gains. Best-case evaluations showed that students could achieve at least the same level of proficiency as conventional instruction in one third the time. Empirical studies showed that students were learning skills in production-rule units and that the best tutorial interaction style was one in which the tutor provides immediate feedback, consisting of short and directed error messages. The tutors appear to work better if they present themselves to students as nonhuman tools to assist learning rather than as emulations of human tutors. Students working with these tutors display transfer to other environments to the degree that they can map the tutor environment into the test environment. These experiences have coalesced into a new system for developing and deploying tutors. This system involves first selecting a problem-solving interface, then constructing a curriculum under the guidance of a domain expert, then designing a cognitive model for solving problems in that environment, then building instruction around the productions in that model, and finally deploying the tutor in the classroom. New tutors are being built in this system to achieve the NCTM standards for high school mathematics in an urban setting. (http://www.dtic.mil/cgi-bin/GetTRDoc?AD=ADA312246)

A taxonomy of approaches to teach spelling

This paper presents a comprehensive taxonomy for classifying major approaches to teach spelling. The Traditional Approach is based on linguistic theory, and is predicated on the assumption that there is regularity to the spelling of words in the English language. Many commercially-based spelling programs use the Traditional Approach. The Remedial Approach can be divided into four subcategories, two of which employ multisensory methods. Horn's remedial method combines elements of visualization, pronunciation, and spelling recall, whereas the phonovisual method is phonetically based, and stresses visual and auditory discrimination of letter sounds. Methods under the Specialized Approach can be considered discrete spelling interventions based on applied behavior analysis, direct instruction, spelling rules, cognitive behavior modification, peer tutoring, or computer applications. The authors' position is that the Specialized Approach offers the optimum combination of instructional efficiency and effectiveness consistent with the concept of the least restrictive alternative. We believe that self-correction is the best exemplar of this approach.

Cognitive tutoring as a mental health service for children with learning problems.

Cognitive tutoring as a mental health service for children with learning problems.

Cognitive tutoring as a mental health service for children with learning problems.

Cognitive tutoring as a mental health service for children with learning problems.

College students as cognitive tutors in a child guidance setting.

College students as cognitive tutors in a child guidance setting.

College students as cognitive tutors in a child guidance setting.

College students as cognitive tutors in a child guidance setting.