Fuzzy Logic in Student Modeling - Advances in Personalized Web-Based Education - page 26

of the student's features, such as knowledge and individual traits, so as to be
accessible for offering adaptation (Brusilovsky and Millán 2007). The adaptive
and/or personalized educational system consults the student model and delivers
the learning material to each individual learner with respect to her/his personal
characteristics.
However, student modeling in many cases deals with uncertainty. Learning
and student's diagnosis are complex. They are defined by many factors and are
depended on tasks and facts that are uncertain and, usually, unmeasured. One pos-
sible approach to deal with this is fuzzy logic, which was introduced by Zaheh
(1965) as a methodology for computing with words in order to handle uncer-
tainty. It encounters the uncertainty problems that are caused by incomplete data
and human subjectivity (Drigas et al. 2009). Chrysafiadi and Virvou (2012) have
showed that the integration of fuzzy logic into the student model of an ITS can
increase learners' satisfaction and performance, improve the system's adaptivity
and help the system to make more valid and reliable decisions. Consequently, fuzzy
logic techniques are able to analyze the students' knowledge level, needs and
behavior and to make the right decision about the instructional model that has to
be applied for each individual learner.
The issue of fuzzy logic and how it can be used in student modeling are pre-
sented in the remainder of this chapter. In particular, an overview of the fuzzy logic
theory and fuzzy sets are described. Also, applications of fuzzy logic in student
modeling are presented. Furthermore, the use of fuzzy logic in the representation
of the knowledge domain of an adaptive and/or personalized tutoring system is
described. In addition, a novel rule-based fuzzy logic system for modeling auto-
matically the learning or forgetting process of a student is presented. Finally, a
brief discussion and the conclusions drawn from this work are presented.
2.2 An Overview of Fuzzy Logic
Fuzzy logic was introduced by Zadeh (1965) to encounter imprecision and uncer-
tainty. It deals with reasoning that is approximate rather than fixed and exact. It is
a precise logic of imprecision and approximate reasoning (Zadeh 1975, 1979). In
other words, fuzzy logic is able to reason and make rational decisions in circum-
stances of imprecision, uncertainty, human subjectivity, incomplete information
and deficient computations (Zadeh 2001).
The basic element of the fuzzy logic theory is the fuzzy set. A fuzzy set
describes a characteristic, thing, fact or state. For example, 'novice' is a fuzzy set
that describes the student's knowledge level, 'young' is a fuzzy set that describes
the person's age, 'cold' is a fuzzy set that describes the environment's tempera-
ture, 'tall' is a fuzzy set that describes the person's height, 'loud' is a fuzzy set that
describes the sound's intensity, 'close' is a fuzzy set that describes the distance
between two objects. The fuzzy sets that describe an element have no concrete
limits (Fig. 2.1 ).