A multivariate Elo-based learner model for adaptive educational systems

Solmaz Abdi, Hassan Khosravi, Shazia Sadiq, Dragan Gasevic

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

4 Citations (Scopus)


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 multivari-ate 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.

Original languageEnglish
Title of host publicationProceedings of the 12th International Conference on Educational Data Mining
EditorsCollin F. Lynch, Agathe Merceron, Michel Desmarais, Roger Nkambou
Place of PublicationMontreal Canada
PublisherPresses De I Universite Du Quebec
Number of pages6
ISBN (Electronic)9781733673600
Publication statusPublished - 2019
EventEducational Data Mining 2019 - Montreal , Canada
Duration: 2 Jul 20195 Jul 2019
Conference number: 12th


ConferenceEducational Data Mining 2019
Abbreviated titleEDM 2019
Internet address

Cite this