Knowledge tracing: Modeling the acquisition of procedural knowledge

  title={Knowledge tracing: Modeling the acquisition of procedural knowledge},
  author={Albert T. Corbett and John R. Anderson},
  journal={User Modeling and User-Adapted Interaction},
This paper describes an effort to model students' changing knowledge state during skill acquisition. [] Key Method As the student works, the tutor also maintains an estimate of the probability that the student has learned each of the rules in the ideal model, in a process calledknowledge tracing. The tutor presents an individualized sequence of exercises to the student based on these probability estimates until the student has ‘mastered’ each rule.

Knowledge Tracing Models’ Predictive Performance when a Student Starts a Skill

Results from this research show that much of the difference in performance between classic algorithms such as BKT (Bayesian Knowledge Tracing) and PFA (Performance Factors Analysis), as compared to a modern algorithm such as DKVMN (Dynamic Key-Value Memory Networks), comes down to the first attempts of a skill.

A New Interpretation of Knowledge Tracing Models' Predictive Performance in Terms of the Cold Start Problem

Results from this research show that much of the difference in performance between classic algorithms such as BKT (Bayesian Knowledge Tracing) and PFA (Performance Factors Analysis), as compared to a modern algorithm such as DKVMN (Dynamic Key-Value Memory Networks), comes down to the first attempts of a skill.

Tutor Modeling vs . Student Modeling

The current paradigm in student modeling, Knowledge Tracing, has continued to show the power of its simplifying assumption of knowledge as a binary and monotonically increasing construct, the value

Investigating Knowledge Tracing Models using Simulated Students

This work conducts experiments using agents generated by Apprentice Learner (AL) Architecture to investigate the online use of different knowledge tracing models (Bayesian Knowledge Tracing and the Streak model), and successfully A/B test these different approaches using simulated students.

Automated Cognitive Analyses for Intelligent Tutoring Systems

  • S. BannoHayder MuradM. Sallal
  • Education
    2020 IEEE/ACM International Conference on Big Data Computing, Applications and Technologies (BDCAT)
  • 2020
ModPFA was developed by adding the hinting parameter to the original PFA formula and has scoring procedure and knowledge level estimation for each student, and results have shown great improvement in terms of performance estimation in the ModPFA compared to PFA.

Generalized Knowledge Tracing: A Constrained Framework for Learner Modeling

It is argued that to be maximally applicable a learner model needs to adapt to student differences, rather than needing to be pre-parameterized with the level of each student's ability, to strengthen the applicability to learning technology.

Modeling Student Knowledge: Cognitive Tutors in High School and College

The role of student modeling in making the transition from the research lab to widespread classroom use is examined, university-based efforts to empirically validate student modeled in the ACT Programming Tutor are described, and a description of the key role that student modeling plays in formative evaluations of the Cognitive Algebra II Tutor is described.

Predicting Individualized Learner Models Across Tutor Lessons

It is found that best-fitting student parameters trained on previous lessons do not directly transfer to new lessons; however, one can effectively predict the student parameters for the new lesson by using features derived from prior lessons, and prior to tutor text-reading transaction data.

Tutor Modeling Versus Student Modeling

Harnessing the same simplifying assumption of learning used in student modeling, this model can be turned on its head to effectively tease out the tutor attributes causing learning and begin to optimize the tutor model to benefit the student model.

Using Bayesian Networks to Manage Uncertainty in Student Modeling

The basic mechanisms that allow Andes’ student models to soundly perform assessment and plan recognition, as well as the Bayesian network solutions to issues that arose in scaling up the model to a full-scale, field evaluated application are described.



Student Modeling in an Intelligent Programming Tutor

The predictive validity of this modeling process is assessed, the implications for the rules in the ideal student model are examined, and the recommendations for remediation are examined.

Cognitive Tutors: Lessons Learned

The 10-year history of tutor development based on the advanced computer tutoring (ACT) theory is reviewed, finding that a new system for developing and deploying tutors is being built to achieve the National Council of Teachers of Mathematics (NCTM) standards for high-school mathematics in an urban setting.

General Principles for an Intelligent Tutoring Architecture.

The major outcome of the research project has been a set of ideas for developing intelligent tutoring systems and an architecture for implementing these ideas which has been used so far to teach LISP, prolog, and pascal at CMU, and NYNEX has adapted it to teach COBOL.

Skill Acquisition and the LISP Tutor

An analysis of student learning with the LISP tutor indicates that while LISP is complex, learning it is simple. The key to factoring out the complexity of LISP is to monitor the learning of the 500

Transfer of programming skills in novice lisp learners

This research addresses novices' learning of the programming language LISP and transfer between coding, debugging, and evaluation and supports an identical elements theory of transfer based on ACT* learning mechanisms.

Mind Bugs: The Origins of Procedural Misconceptions

From the Publisher: As children acquire arithmetic skills, they often develop "bugs" - small, local misconceptions that cause systematic errors. Mind Bugs combines a novel cognitive simulation

Bypassing the intractable problem of student modelling

Practical guidelines and changes in philosophical approach are suggested which may help in building effective student models within intelligent tutoring systems.

Rules of the Mind

Production Systems and the ACT-R Theory and the Identical Elements Theory of Transfer.