Categorizing E-Learner Attributes in Personalized E-learning Environments: A Systematic Literature Review
Background: The development of learner models in learning management systems is among the most significant steps in designing personalized e-learning environments. The primary purpose of this modeling is to extract user characteristics in order to personalize the learning process based on learners’...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Shiraz University of Medical Sciences
2021-03-01
|
| Series: | Interdisciplinary Journal of Virtual Learning in Medical Sciences |
| Subjects: | |
| Online Access: | https://ijvlms.sums.ac.ir/article_47322_623798cd8da887c41831a650595891c1.pdf |
| Summary: | Background: The development of learner models in learning management systems is among the most significant steps in designing personalized e-learning environments. The primary purpose of this modeling is to extract user characteristics in order to personalize the learning process based on learners’ needs, learning style, personality, and individual circumstances. Methods: The present study provides a review of published literature over the past 20 years in academic databases including IEEE, Sciencedirect, Wiley, and Springer. The search was limited to the studies on the personalization of e-learning environments based on learner characteristics, specifically the ones providing a reliable method for integrating these characteristics, as appropriate input variables, in the design of personalized e-learning systems. Results: This study proposed a new method of classifying the learner characteristics as the variables for designing a personalized e-learning system. A total of 111 papers were considered for analysis. In the end, 22 influential learner characteristics were extracted and classified into six subcategories, namely cognitive, motivational, behavioral, emotional, metacognitive aspects, and combined domains. The proposed classification method was also compared with available related categorizations to demonstrate this method’s advantage in designing a personalized e-learning environment. Conclusion: The findings represent the learning criteria that can be utilized in designing adaptive learning systems. Moreover, it can also aid other researchers in this field to achieve a better perspective in learner modeling. Applying these characteristics as input design variables in personalized e-learning systems can result in a better solution for personalization. |
|---|---|
| ISSN: | 2476-7263 2476-7271 |