Bringing AI to E-Learning: The Case of a Modular, Highly Adaptive System

2. State Of The Art

Adaptive e-learning systems often employ models of the user. A user model is a representation of the user’s properties and characteristics. Before a user model can be used it has to be constructed. This process requires much effort especially for gathering the required information and for generating a model of the user.

The behavior of an adaptive system varies according to the data from the user model and the user profile. In (Koch, 2000) there is a description of the necessity of applying user models as follows: “Users are different: they have different background, different knowledge about a subject, different preferences, goals and interests. To individualize, personalize or customize actions a user model is needed that allows for selection of individualized responses to the user.”

In the context of e-learning, adaptive systems are more specialized and focus on the adaptation of the learning content and its presentation. According to (Mödritscher et al., 2004), an adaptive system focuses on how the knowledge is learned by the student and pays attention to learning activities, cognitive structures and the context of the learning material.

In Figure 1, the structure of an adaptive system, according to (Brusilovski & Maybury, 2002) with three stages during the process of adaptation is shown. It controls the process of collecting data about the user, the process of building up the user model (user modeling) and the adaptation process.

Figure 1.

The structure of an adaptive system