Student Modeling for Personalized Education: A Review of the Literature - Advances in Personalized Web-Based Education - page 9

Fig. 1.8 A Bayesian network
each time considering a set of criteria and model specifications (Shakouri and
Menhaj 2008). 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. Therefore, several researchers have incorporated fuzzy
logic techniques in student modeling.
1.2.6.2 Bayesian Networks
Bayesian Networks is another well-established tool for representing and reasoning
about uncertainty in student models (Conati et al. 2002). BN's graphical repre-
sentation, sound mathematical foundations and ability to represent uncertainty
using probabilities make them attractive to many researchers (Jameson 1996;
Liu 2008; Desmarais and Baker 2012). Indeed, the presence of capable and
robust Bayesian libraries (e.g. SMILE), which can be easily integrated into the
existing or new student modeling applications, facilitates the adoption of BNs in
student modeling (Millán et al. 2010). A Bayesian Network (BN) is a directed
acyclic graph in which nodes represent variables and arcs represent probabilistic
dependence or causal relationships among variables (Pearl 1988) (Fig. 1.8 ). The
causal information encoded in BN facilitates the analysis of action sequences,
observations, consequences and expected utility (Pearl 1996). In student
modeling nodes of a BN can represent the different components/dimensions of a
student such as knowledge, misconceptions, emotions, learning styles, motivation,
goals etc.