An Enhanced ELO-Based Student Model for Polychotomously Scored Items in Adaptive Educational System
Saved in:
| Title: | An Enhanced ELO-Based Student Model for Polychotomously Scored Items in Adaptive Educational System |
|---|---|
| Language: | English |
| Authors: | Bingxue Zhang, Yang Shi, Yuxing Li, Chengliang Chai, Longfeng Hou |
| Source: | Interactive Learning Environments. 2023 31(9):5477-5494. |
| Availability: | Routledge. Available from: Taylor & Francis, Ltd. 530 Walnut Street Suite 850, Philadelphia, PA 19106. Tel: 800-354-1420; Tel: 215-625-8900; Fax: 215-207-0050; Web site: http://www.tandf.co.uk/journals |
| Peer Reviewed: | Y |
| Page Count: | 18 |
| Publication Date: | 2023 |
| Document Type: | Journal Articles Reports - Research |
| Descriptors: | Electronic Learning, Models, Students, Individualized Instruction, Academic Achievement, Cognitive Ability, Test Items, Achievement Rating, Student Evaluation |
| DOI: | 10.1080/10494820.2021.2010099 |
| ISSN: | 1049-4820 1744-5191 |
| Abstract: | The adaptive learning environment provides learning support that suits individual characteristics of students, and the student model of the adaptive learning environment is the key element to promote individualized learning. This paper provides a systematic overview of the existing student models, consequently showing that the Elo rating system has greater potential as compared to the other models regarding application in the online learning environment. Based on the Elo model, this study proposes the EELO, an enhanced Elo rating system, in consideration of the application scenarios of polychotomously scored items and multi-dimensional granularity evaluations not covered by the basic Elo rating system. The EELO model estimating students' cognitive abilities and predicting their future performances on unknown questions is evaluated based on one public set (Assigment2) and one proprietary dataset (HSK), and achieved an AUC of 0.92 for Assigment2 and 0.84 for HSK, which shows that the EELO model has the best performance regarding the above-mentioned objectives as compared with the latest extensions of the IRT and BKT models. Subsequently, the EELO model was tested and applied successfully in a real large-scale online learning environment to demonstrate the potential of the EELO model in adaptive learning applications. |
| Abstractor: | As Provided |
| Entry Date: | 2023 |
| Accession Number: | EJ1403011 |
| Database: | ERIC |
| Abstract: | The adaptive learning environment provides learning support that suits individual characteristics of students, and the student model of the adaptive learning environment is the key element to promote individualized learning. This paper provides a systematic overview of the existing student models, consequently showing that the Elo rating system has greater potential as compared to the other models regarding application in the online learning environment. Based on the Elo model, this study proposes the EELO, an enhanced Elo rating system, in consideration of the application scenarios of polychotomously scored items and multi-dimensional granularity evaluations not covered by the basic Elo rating system. The EELO model estimating students' cognitive abilities and predicting their future performances on unknown questions is evaluated based on one public set (Assigment2) and one proprietary dataset (HSK), and achieved an AUC of 0.92 for Assigment2 and 0.84 for HSK, which shows that the EELO model has the best performance regarding the above-mentioned objectives as compared with the latest extensions of the IRT and BKT models. Subsequently, the EELO model was tested and applied successfully in a real large-scale online learning environment to demonstrate the potential of the EELO model in adaptive learning applications. |
|---|---|
| ISSN: | 1049-4820 1744-5191 |
| DOI: | 10.1080/10494820.2021.2010099 |
