A Multivariate ELO-based Learner Model for Adaptive Educational Systems

The Elo rating system has been recognised as an effective method for modelling students and items within adaptive educational systems. The existing Elo-based models have the limiting assumption that items are only tagged with a single concept and are mainly studied in the context of adaptive testing systems. In this paper, we introduce a multivariate Elo-based learner model that is suitable for the domains where learning items can be tagged with multiple concepts, and investigate its fit in the context of adaptive learning. To evaluate the model, we first compare the predictive performance of the proposed model against the standard Elo-based model using synthetic and public data sets. Our results from this study indicate that our proposed model has superior predictive performance compared to the standard Elo-based model, but the difference is rather small. We then investigate the fit of the proposed multivariate Elo-based model by integrating it into an adaptive learning system which incorporates the principles of open learner models (OLMs). The results from this study suggest that the availability of additional parameters derived from multivariate Elo-based models have two further advantages: guiding adaptive behaviour for the system and providing additional insight for students and instructors.

[1]  Michel C. Desmarais,et al.  A review of recent advances in learner and skill modeling in intelligent learning environments , 2012, User Modeling and User-Adapted Interaction.

[2]  Judy Kay,et al.  Open Learner Models , 2010, Advances in Intelligent Tutoring Systems.

[3]  Radek Pelánek,et al.  Elo-based learner modeling for the adaptive practice of facts , 2017, User Modeling and User-Adapted Interaction.

[4]  Albert T. Corbett,et al.  The Knowledge-Learning-Instruction Framework: Bridging the Science-Practice Chasm to Enhance Robust Student Learning , 2012, Cogn. Sci..

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

[6]  Alfred Kobsa.  User Modeling and User-Adapted Interaction , 2005, User Modeling and User-Adapted Interaction.

[7]  Albert T. Corbett,et al.  Cognitive Tutor: Applied research in mathematics education , 2007, Psychonomic bulletin & review.

[8]  Judy Kay,et al.  Open learner models and learning analytics dashboards: a systematic review , 2018, LAK.

[9]  S. Klinkenberg,et al.  Computer adaptive practice of Maths ability using a new item response model for on the fly ability and difficulty estimation , 2011, Comput. Educ..

[10]  Michel C. Desmarais,et al.  On the Faithfulness of Simulated Student Performance Data , 2010, EDM.

[11]  Joseph Jay Williams,et al.  RiPPLE: A Crowdsourced Adaptive Platform for Recommendation of Learning Activities , 2019, J. Learn. Anal..

[12]  Briana B. Morrison,et al.  Khan academy gamifies computer science , 2014, SIGCSE.

[13]  Alexandros Paramythis,et al.  Adaptive Learning Environments and e-Learning Standards. , 2004 .

[14]  Wim van den Noortgate,et al.  Monitoring Learners' Proficiency: Weight Adaptation in the Elo Rating System , 2011, EDM.

[15]  Hassan Khosravi,et al.  RiPLE: Recommendation in Peer-Learning Environments Based on Knowledge Gaps and Interests , 2017, EDM.

[16]  Kenneth R. Koedinger,et al.  A Data Repository for the EDM Community: The PSLC DataShop , 2010 .

[17]  De Ayala,et al.  The Theory and Practice of Item Response Theory , 2008 .

[18]  Mohsen Alavash,et al.  Adaptive experiments with a multivariate Elo-type algorithm , 2015, Behavior research methods.

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

[20]  Radek Pelanek,et al.  Applications of the Elo rating system in adaptive educational systems , 2016, Comput. Educ..

[21]  Kenneth R. Koedinger,et al.  Learning Factors Analysis - A General Method for Cognitive Model Evaluation and Improvement , 2006, Intelligent Tutoring Systems.