Elo-based Learner Modeling for the Adaptive Practice of Facts
| Authors | |
|---|---|
| Year of publication | 2017 |
| Type | Article in Periodical |
| Magazine / Source | User Modeling and User-Adapted Interaction |
| MU Faculty or unit | |
| Citation | |
| web | http://dx.doi.org/10.1007/s11257-016-9185-7 |
| Doi | http://dx.doi.org/10.1007/s11257-016-9185-7 |
| Field | Informatics |
| Keywords | Learner modeling;Computerized adaptive practice;Elo rating system;Model evaluation;Factual knowledge |
| Description | We investigate applications of learner modeling in a computerized adaptive system for practicing factual knowledge. We focus on areas where learners have widely varying prior knowledge. We propose a modular approach to the development of such adaptive practice systems: decomposing the system design into estimation of prior knowledge, estimation of current knowledge, and construction of questions. We provide a detailed discussion of learner models for both estimation steps, including a novel use of the Elo rating system for learner modeling. We implemented the proposed approach in a system for practice of geography facts; the system is widely used and allows us to perform evaluation of all three modules. We compare predictive accuracy of different learner models, discuss insights gained from learner modeling, and also impact of different variants of the system on learners engagement and learning. |
| Related projects: |