The Optimization by Using the Learning Styles in the Adaptive Hypermedia Applications

The Optimization by Using the Learning Styles in the Adaptive Hypermedia Applications

Lamia Hamza, Guiassa Yamina Tlili
DOI: 10.4018/IJWLTT.2018040102
(Individual Articles)
No Current Special Offers


This article addresses the learning style as a criterion for optimization of adaptive content in hypermedia applications. First, the authors present the different optimization approaches proposed in the area of adaptive hypermedia systems whose goal is to define the optimization problem in this type of system. Then, they present the architecture of their proposed system. The first step involves choosing a learning style model. The selection of this style is done by using a dedicated questionnaire answered by a learner. Then a modeling of the learner is completed based on his learning style. Finally, content that is to be presented to the learner is managed by a content generator module, depending on the model of the learner. Built on methods and techniques proposed for modeling and adaptation, the adaptive hypermedia system based on learning styles provides optimized adaptations. The authors' approach has been experimentally validated and the results are encouraging.
Article Preview

2. Existing Adaptive Content Optimization Approaches

In this section, we present the optimization problem in the field of adaptive hypermedia applications. We base our presentation on the study of some adaptive content optimization approaches to compare with our proposed solution.

2.1. GAITS Approach

GAITS was one of the first educational hypermedia systems using genetic optimization algorithms. Supervised education techniques are used, the teacher assigns an educational goal for each student before training begins (Quafafou, 1993).

In order to provide optimal educational content, the tutor interacts with the learner using predefined dialogues. These dialogs consist of a header and a body. The header contains the preliminary knowledge required to use this dialogue as a candidate of the current lesson, a learning level and a learning strategy to present the lesson. The body represents the educational material that defines the interactions (exhibition, question / answer, games, etc.) (Mock, 1996).

2.2. Approach by Ant Colony

Several research studies have used algorithms ant colonies (a class of evolutionary algorithms recently proposed for difficult optimization problems). The goal was to track the learner when navigating through the links courses and study his footsteps.

With a simple decomposition of content in sections and units, the ant colony algorithm could solve the problem of guiding users on their path. The main mechanisms used in this algorithm is the propagation of information (the effectiveness of the teaching of content units, relevance of bows, and the tendency of users) accumulated by the system through user navigation between units content. This information's communication mechanism described the operation mode of the ant colony. The objective of this switching device is to guide the user to the most consistent unit. (Haddi et al., 2008).

Another approach consists to assimilate the user as the ant (Dahbi et al., 2014). Modeling content in the form of a directed graph allows applying this algorithm. Each node of the graph represents a concept, each directed arc represents the opportunity to spend this concept to another. The user can then be assimilated to an ant looking for the best way to achieve the goal., passing the tests related to the final lesson of this course. The best way forward is built gradually through the pheromone left by the user throughout its course, failures and successes. Such approaches are used for groups of users by recording track of users during navigation in the set of content.

Complete Article List

Search this Journal:
Volume 19: 1 Issue (2024)
Volume 18: 2 Issues (2023)
Volume 17: 8 Issues (2022)
Volume 16: 6 Issues (2021)
Volume 15: 4 Issues (2020)
Volume 14: 4 Issues (2019)
Volume 13: 4 Issues (2018)
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing