Recommending suitable learning paths according to learners’ preferences: Experimental research results
Autor: | Eugenijus Kurilovas, Valentina Dagiene, Inga Zilinskiene |
---|---|
Rok vydání: | 2015 |
Předmět: |
Proactive learning
Preference learning Learning classifier system business.industry Computer science Active learning (machine learning) Algorithmic learning theory Machine learning computer.software_genre Robot learning Synchronous learning Human-Computer Interaction Arts and Humanities (miscellaneous) Artificial intelligence Instance-based learning business computer General Psychology |
Zdroj: | Computers in Human Behavior. 51:945-951 |
ISSN: | 0747-5632 |
Popis: | Recommending suitable learning paths according to learners' preferences.Experimental research results.Learners behaviour and learning styles. The paper deals with the problem of personalising learning units with the main focus on finding personalised learning paths in learning units. Finding suitable learning paths is based on students' needs in terms of their learning styles. It has been shown that learning path in static and dynamic learning units can be selected by applying artificial intelligence techniques, e.g. a swarm intelligence model, mainly by adapting ant colony optimisation method based on collaboration and pheromones. In the paper, experimental results of applying the proposed approach in practise are presented. The results of empirical experiment have shown that learning in the proposed prototype of e-learning system applying created recommending method improves students' learning results and saves their learning time. This fact indicates that the developed adaptive method for personalising learning units is practically applicable in e-learning and enhances the learning quality. |
Databáze: | OpenAIRE |
Externí odkaz: |