Machine Learning Techniques for Knowledge Tracing: A Systematic Literature Review

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.

[1]  Pedro M. Domingos.  A few useful things to know about machine learning , 2012, Commun. ACM.

[2]  Radek Pelánek,et al.  Metrics for Evaluation of Student Models , 2015, EDM.

[3]  Holger H. Hoos,et al.  A survey on semi-supervised learning , 2019, Machine Learning.

[4]  John R. Anderson,et al.  Knowledge tracing: Modeling the acquisition of procedural knowledge , 2005, User Modeling and User-Adapted Interaction.

[5]  Pengyu Hong,et al.  Neural Knowledge Tracing , 2017, BFAL.

[6]  Biao Li,et al.  Learning Ability Community for Personalized Knowledge Tracing , 2020, APWeb/WAIM.

[7]  D. Moher,et al.  Preferred reporting items for systematic reviews and meta-analyses: the PRISMA statement. , 2010, International journal of surgery.

[8]  Judea Pearl,et al.  Probabilistic reasoning in intelligent systems - networks of plausible inference , 1991, Morgan Kaufmann series in representation and reasoning.

[9]  Min Chi,et al.  Deep Learning vs. Bayesian Knowledge Tracing: Student Models for Interventions , 2018 .

[10]  Jürgen Schmidhuber,et al.  Deep learning in neural networks: An overview , 2014, Neural Networks.

[11]  José-Luis Pérez-de-la-Cruz,et al.  Learning Bayesian Networks for Student Modeling , 2015, AIED.

[12]  Michael Eagle,et al.  Estimating Individual Differences for Student Modeling in Intelligent Tutors from Reading and Pretest Data , 2016, ITS.

[13]  Etienne Wenger,et al.  Artificial Intelligence and Tutoring Systems: Computational and Cognitive Approaches to the Communication of Knowledge , 1987 .

[14]  Nour El Mawas,et al.  Towards Open Learner Models Including the Flow State , 2020, UMAP.

[15]  Serge Garlatti,et al.  As One Size Doesn't Fit All, Personalized Massive Open Online Courses Are Required , 2018, CSEDU.

[16]  Eurico Carrapatoso,et al.  User Modeling in Adaptive Hypermedia Educational Systems , 2008, J. Educ. Technol. Soc..

[17]  Yong Hu,et al.  Systematic literature review of machine learning based software development effort estimation models , 2012, Inf. Softw. Technol..

[18]  Lars Schmidt-Thieme,et al.  Vygotsky Based Sequencing Without Domain Information: A Matrix Factorization Approach , 2014, CSEDU.

[19]  Aggelos K. Katsaggelos,et al.  Knowledge Tracing to Model Learning in Online Citizen Science Projects , 2020, IEEE Transactions on Learning Technologies.

[20]  Wided Lejouad Chaari,et al.  Knowledge tracing with an intelligent agent, in an e-learning platform , 2018, Education and Information Technologies.

[21]  Fredrik Olsson,et al.  A literature survey of active machine learning in the context of natural language processing , 2009 .

[22]  Lorella Giannandrea,et al.  A literature review on Intelligent Tutoring Systems and on studentprofiling , 2013 .

[23]  John R. Anderson,et al.  Student modeling in the ACT Programming Tutor. , 1995 .

[24]  Nykan Mirchi,et al.  Artificial Intelligence in Medical Education: Best Practices Using Machine Learning to Assess Surgical Expertise in Virtual Reality Simulation. , 2019, Journal of surgical education.

[25]  Dit-Yan Yeung,et al.  Dynamic Key-Value Memory Networks for Knowledge Tracing , 2016, WWW.

[26]  Davide Chicco,et al.  Ten quick tips for machine learning in computational biology , 2017, BioData Mining.

[27]  Rabi Narayan Behera,et al.  A Survey on Machine Learning: Concept,Algorithms and Applications , 2017 .

[28]  Li-Pang Chen,et al.  Mehryar Mohri, Afshin Rostamizadeh, and Ameet Talwalkar: Foundations of machine learning, second edition , 2019, Statistical Papers.

[29]  Cristina Conati,et al.  Bayesian Student Modeling , 2010, Advances in Intelligent Tutoring Systems.

[30]  Kenneth R. Koedinger,et al.  Individualized Bayesian Knowledge Tracing Models , 2013, AIED.

[31]  Leonidas J. Guibas,et al.  Deep Knowledge Tracing , 2015, NIPS.

[32]  Neil T. Heffernan,et al.  Blending Assessment and Instructional Assisting , 2005, AIED.

[33]  Irwin King,et al.  Topological Order Discovery via Deep Knowledge Tracing , 2016, ICONIP.

[34]  A. Granić,et al.  Anatomy of Student Models in Adaptive Learning Systems: A Systematic Literature Review of Individual Differences from 2001 to 2013 , 2015 .

[35]  Filippo Sciarrone,et al.  K-OpenAnswer: a simulation environment to analyze the dynamics of massive open online courses in smart cities , 2020, Soft Computing.

[36]  Kenneth R. Koedinger,et al.  Performance Factors Analysis - A New Alternative to Knowledge Tracing , 2009, AIED.

[37]  Zachary A. Pardos,et al.  Deep Knowledge Tracing for Free-Form Student Code Progression , 2018, AIED.

[38]  Dongjo Shin,et al.  A Systematic Review on Data Mining for Mathematics and Science Education , 2020, International Journal of Science and Mathematics Education.