PHD theses : Computer Science

Permanent URI for this collectionhttps://repository.neelain.edu.sd/handle/123456789/12169

Browse

Filters

20181

Settings

End date: 2019Subject: search.filters.subject.(AEHSs)

Search Results

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    A Multi-Traits Dynamic User Model for Adaptive Educational Hypermedia Systems
    (Al Neelain University, 2018-01) Nafisa Abdou Hassan Ahmed
    Adaptive Educational hypermedia systems (AEHSs), was one of the first application areas for Adaptive Hypermedia. AEHSs, which deliver a personalized content to users, are evolved as an alternative educational model to the traditional one that provides same content to all users. An AEHS consist of three main components; the domain model (DM), which is the knowledge domain area where the AEHS is used as a learning resource. The user model (UM), which is a collection of user characteristics that are used to adapt the content in the domain model. And the adaptation model (AM) which describes the parts of the hypermedia system that to be adapted and the conditions under which this adaptation is to occur. In AEHS, the user model is the heart of the system, based on which the adaptation model personalize the content. A user model in AEHS is either static, where the information about the user characteristics is collected and updated before starting the adaptation or in habitual intervals, or dynamic, where the user information is updated continuously as the user interact with the system. In this research, a Multi Traits Dynamic User Model for Adaptive Educational Hypermedia Systems (AEHS) was proposed. The model incorporates four dynamic user characteristics; knowledge, learning style, goals, and behavior. The proposed dynamic user model is build to support adaptivity in lesson-based AEHS using those criterions. A user characteristics valuation algorithm is developed to evaluate the user's dynamic characteristics before moving to the next lesson. The valuation algorithm is based on link analysis on the user’s set of navigation links in the current lesson before the knowledge test. The algorithm assigns values to user learning style, goals and behavior, and knowledge and passes the valuation to the adaptation engine to generate adapted content of the next lesson page. The test of the model shows its flexibility and high adaptivity to user knowledge, learning style, goals, and behavior.