The advent and omnipresence of information systems have been revolutionizing and changing not only the way we communicate access information and conduct businesses, but also the way we learn. In the world of pervasive Internet, learners are also evolving: the so-called “digital natives” want to be in constant communication with their peers, they expect an individualized instruction and a personalized learning environment. In this context, we present such an adaptive educational system, called WELSA, illustrating it with a course module on “Artificial Intelligence”. According to Brusilovsky and Millan (2007), adaptation can be done with respect to various factors, such as knowledge, interests, goals, background, individual traits and context of work. In this paper we base our adaptation on one of the students' individual traits, namely their learning style (i.e., a specific manner of approaching a learning task, the preferred learning strategies activated in order to fulfill that task).
Motivation
Our endeavor was motivated by several aspects.
First, many educational psychologists support the use of learning styles, claiming that they have an important effect on the learning process (Popescu, 2010a); however this is not to say that the domain is free from controversies (Coffield et al., 2004).
Secondly, during the past several years, quite a few researchers dedicated their time to the development of learning style based adaptive educational systems (LSAES), as we will see in the next section. Most of them reported positive experimental results with their systems, finding improvements in student learning gain and/or satisfaction (Bajraktarevic et al., 2003; Carver et al., 1999; Graf et al., 2009; Lee et al., 2005; Limongelli et al., 2009; Papanikolaou et al., 2003; Sangineto et al., 2008; Triantafillou et al., 2004; Wang et al., 2008). Once again, contrary results have also been reported, with (Brown et al., 2009) being a representative study in this respect.
Thirdly, due to the huge expansion of the Web, the amount of information made available in current e-learning systems is very large, definitely larger than what could be presented by traditional teaching means. While being a positive aspect, this availability can also have a downside - it could easily become overwhelming for the students. It is therefore of a particular importance to filter the content in order to avoid cognitive overload of the learners. Furthermore, it is important to decide how to best present this content and in what sequence (the navigation type).