Information Technology Reference
In-Depth Information
techniques are applied to the main components of the ITS' architecture. In other
words, artificial intelligence techniques are applied to the knowledge domain rep-
resentation, to the student model and to the pedagogical model (Badaracco and
Martinez 2013). Researches in ITS include researches in techniques that will make
an ITS to 'behave' in a more intelligent way (Conati 2009), which means to diag-
nose the student's learning status and needs in a more effective way and manage
the instructional and pedagogical strategy as a real domain expert. Many of these
researches have been extended to researches in student model. This has happened
due to the fact that the student model is the base for personalization in computer-
based educational applications.
As a consequence, a crucial factor for designing an effective ITS and/or an
adaptive educational system is the construction of an effective student model. In
order to construct a student model, it has to be considered what information and
data about a student should be gathered, how it will update in order to keep it up-
to-date, and how it will be used in order to provide adaptation (Millán et al. 2010;
Nguyen and Do 2009). In fact, when a student model is constructed, the following
three questions have to be answered:
(i) What are the characteristics of the user we want to model?
(ii) How we model them?
(iii) How we use the user model?
The target of this chapter is to present the student's characteristics that are usually
modeled. Furthermore, the student modeling techniques that are used in the literature
in relation to each student's characteristic are presented.
1.2 Student Modeling Techniques and Methods
1.2.1 The Overlay Method
One of the most popular and common used student models is the overlay model.
It was invented by Stansfield et al. (1976) and has been used in many systems ever
since. The reason for its extensive use is the fact that the overlay model can rep-
resent independently the user knowledge for each concept. According to the over-
lay modeling, the student model is a subset of the domain model (Martins et al.
2008; Vélez et al. 2008), which reflects the expert-level knowledge of the subject
(Brusilovsky and Millán 2007; Liu and Wang 2007) (Fig. 1.3 ). Therefore, the stu-
dent's knowledge is represented as incomplete but no as incorrect. The incomplete
student's knowledge is defined by the differences between her/his and the expert's
set of knowledge (Bontcheva and Wilks 2005; Michaud and McCoy 2004; Staff
2001; Nguyen and Do 2008). According to the overlay student modeling approach,
the knowledge domain is decomposed into individual topics and concepts that
are called elements. Usually, each element is characterized as known or unknown
for the student. However, there are overlay models, in which each element is
Search WWH ::




Custom Search