Authors:
Carlotta Schatten
and
Lars Schmidt-Thieme
Affiliation:
University of Hildesheim, Germany
Keyword(s):
Performance Prediction, Kalman Filter, Matrix Factorization, Student Simulator, Sequencing, Progress Modeling.
Related
Ontology
Subjects/Areas/Topics:
Artificial Intelligence and Decision Support Systems
;
Computer-Supported Education
;
Domain Applications and Case Studies
;
e-Learning
;
e-Learning Platforms
;
Enterprise Information Systems
;
Information Technologies Supporting Learning
;
Intelligent Learning and Teaching Systems
;
Intelligent Tutoring Systems
;
Learning Analytics
;
Simulation and Modeling
;
Simulation Tools and Platforms
Abstract:
One new usage of Learning Analytics in Intelligent Tutoring Systems (ITS) is sequencing based on performance
prediction, which informs sequencers whether a student mastered or not a specific set of skills. Matrix
Factorization (MF) performance prediction is particularly appealing because it does not require tagging involved
skills in tasks. However, MF’s difficult interpretability does not allow to show the student’s state evolution,
i.e. his/her progress over time. In this paper we present a novel progress modeling technique integrating
the most famous control theory state modeler, the Kalman Filter, and Matrix Factorization. Our method, the
Skill Deficiency aware Kalman State Estimation for Matrix Factorization, (1) updates at each interaction the
student’s state outperforming the baseline both in prediction error and in computational requirements allowing
faster online interactions; (2) models the individualized progress of the students over time that could be later
used to develo
p novel sequencing policies. Our results are tested on data of a commercial ITS where other
state of the art methods were not applicable.
(More)