Loading...
A dynamic associative e-learning model based on a spreading activation network
Author(s)
Date Issued
January 1, 2006
Type
Conference Paper
Abstract
Presenting information to an e-learning environment is a challenge, mostly, because of the hypertext/hypermedia nature and the richness of the context and information provides. This paper proposes a dynamic semantic model for e-learning system based on the psycholinguistic theories of human memory; Spreading Activation Network (SAN). This work employs a SAN as a technique to provide the interface's action selection mechanism in an uncertain environment. The paper combines the SAN with the temporal logic to provide an e-learning system that a learning activity level evolves according to their expected contextual relevance. The system differs from the other e-learning by representing dynamic associations between learning activities and the relevance subjects. This system equipped with an Event-Triggered learning interface (context) adaptation component. This component provides multiple parallel processes for perception. These processes provide context screen selection and learning task operation based upon the user current situation. The SAN attempts to achieve a number of goals in an unpredictable complex dynamic environment. Spreading activation explains the predictive top-down effect of knowledge. It supports general heuristics which may be used as the first step of more elaborated methods. This model is suited to deal with the interaction between semantic and episodic memories, as well as many other practical issues regarding e-learning, including the retroactive effect of semantics over perception. The system uses the SAN to activate the most suitable interface screen (context) in response to the current conditions (learning activities) while the system continues working towards the learning objective goal. The paper presents our efforts to realize such e-learning system. The proposed paradigm has been implemented to develop a prototypical system, and the experiments also illustrate the robustness of such an e-learning framework.
Citation
Canadian Conference on Electrical and Computer Engineering, 2472-2475, 2006