Logistic Knowledge Tracing: A Constrained Framework for Learner Modeling

  title={Logistic Knowledge Tracing: A Constrained Framework for Learner Modeling},
  author={Philip I. Pavlik and Luke G Eglington and Leigh Harrell-Williams},
  journal={IEEE Transactions on Learning Technologies},
Adaptive learning technology solutions often use a learner model to trace learning and make pedagogical decisions. The present research introduces a formalized methodology for specifying learner models, logistic knowledge tracing (LKT), that consolidates many extant learner modeling methods. The strength of LKT is the specification of a symbolic notation system for alternative logistic regression models that is powerful enough to specify many extant models in the literature and many new models… 
Assessing the Knowledge State of Online Students - New Data, New Approaches, Improved Accuracy
This study is the first to use four very large sets of student data made available recently from four distinct intelligent tutoring systems and achieves improved accuracy of student modeling by introducing new features that can be easily computed from conventional question-response logs.
Assessing the Performance of Online Students -- New Data, New Approaches, Improved Accuracy
This study is the first to use four very large sets of student data made available recently from four distinct intelligent tutoring systems to train accurate machine learning models that predict the performance of future students.
Modeling the EdNet Dataset with Logistic Regression
The experience with competition from the perspective of educational data mining, a field founded in the learning sciences and connected with roots in psychology and statistics, and how learner model predictions are used to make pedagogical decisions for students are described.
The Mobile Fact and Concept Textbook System (MoFaCTS)
In this project, MoFaCTS is being completely retooled to accept texts from a textbook and to automatically create cloze sentence practice content to help the student learn the material in the text.
Ability Boosted Knowledge Tracing


Bayesian knowledge tracing, logistic models, and beyond: an overview of learner modeling techniques
  • Radek Pelánek
  • Computer Science
    User Modeling and User-Adapted Interaction
  • 2017
A systematic and up-to-date overview of current approaches to tracing learners’ knowledge and skill across interaction with multiple items, focusing in particular on the widely used Bayesian knowledge tracing and logistic models.
Knowledge tracing: Modeling the acquisition of procedural knowledge
An effort to model students' changing knowledge state during skill acquisition and a series of studies is reviewed that examine the empirical validity of knowledge tracing and has led to modifications in the process.
When is Deep Learning the Best Approach to Knowledge Tracing
An extensive empirical comparison on nine real-world datasets is asked to determine which approach makes the most accurate predictions and in what conditions and a discussion of model calibration (reliability) is held, which is crucial for downstream applications of learner performance prediction models.
How to Construct More Accurate Student Models: Comparing and Optimizing Knowledge Tracing and Performance Factor Analysis
In a head to head comparison, it is found that PFA has considerably higher predictive accuracy than KT and that both KT and PFA have relatively low predictive accuracy for cases where students generate incorrect responses, and 2/3 of the model's errors are false positives, indicating a better means of determining when students will make mistakes is needed.
Performance Factors Analysis - A New Alternative to Knowledge Tracing
This paper describes the work to modify an existing data mining model so that it can also be used to select practice adaptively, and compares this new adaptive datamining model (PFA, Performance Factors Analysis) with two versions of LFA and then compares PFA with standard KT.
Comparing Knowledge Tracing and Performance Factor Analysis by Using Multiple Model Fitting Procedures
This study compared the knowledge tracing model and Performance Factor Analysis in terms of their predictive accuracy and parameter plausibility, and examined whether the models' estimated parameter values were plausible.
The Q-matrix Method: Mining Student Response Data for Knowledge
The q-matrix method is proposed, where data from student behavior is “mined” to create concept models of the material being taught, and preliminary results imply that the method can effectively predict which concepts need further review.
Explanatory learner models: Why machine learning (alone) is not the answer
Examples of development of explanatory models of learners that not only accurately predict data but also provide scientific insights and yield practical outcomes are provided.
Move your lamp post: Recent data reflects learner knowledge better than older data
This work investigates several representations of recency, such as the count of prior practice in the AFM model, and the proportion of recent successes with exponential and box kernels, and finds that an exponential decay of a proportion of successes provides the summary of recent practice with the highest predictive accuracy over alternative models.
The Knowledge-Learning-Instruction Framework: Bridging the Science-Practice Chasm to Enhance Robust Student Learning
The Knowledge-Learning-Instruction framework is described, which promotes the emergence of instructional principles of high potential for generality, while explicitly identifying constraints of and opportunities for detailed analysis of the knowledge students may acquire in courses.