Machine Learning Techniques for Knowledge Tracing: A Systematic Literature Review

Sergio Ramirez, Nour El Mawas, Jean Heutte

halshs-03169451, version 1


Machine Learning (ML) techniques are being intensively applied in educational settings. They are employed to predict competences and skills, grade exams, recognize behavioural academic patterns, evaluate open answers, suggest appropriate educational resources, and group or associate students with similar learning characteristics or academic interests. Knowledge Tracing (KT) allows modelling the learner’s mastery of skill and to meaningfully predict student’s performance, as it tracks within the Learner Model (LM) the knowledge state of students based on observed outcomes from their previous educational practices, such as answers, grades and/or behaviours. In this study, we survey commonly used ML techniques for KT figuring in 51 papers on the topic, out of an original search pool of 628 articles from 5 renowned academic sources, encompassing the latest research, based on the PRISMA method. We identify and review relevant aspects of ML for KT in LM that help paint a more accurate panorama on the topic and hence, contribute to alleviate the difficulty of choosing an appropriate ML technique for KT in LM. This work is dedicated to MOOC designers/providers, pedagogical engineers and researchers who need an overview of existing ML techniques for KT in LM.