Student Modeling for Personalized Education: A Review of the Literature - Advances in Personalized Web-Based Education - page 14

Table 1.1 Student modeling approaches in relation to knowledge level
Overlay Stereotypes Constraint-

based
model

Machine
learning

Cognitive
theories

Fuzzy
techniques

Bayesian
networks

Ontologies

Knowledge
level

42.55 % 29.79 % 8.51 % 14.89 % 4.26 % 10.64 % 14.89 % 14.89 %

new student. The student is first assigned to a stereotype category concerning her/
his knowledge level and then the system initializes all aspects of the student model
using the distance weighted k-nearest neighbor algorithm among the students
that belong to the same stereotype category with the new student. A combina-
tion of stereotypes with machine learning techniques has been, also, used in Web-
PTV (Tsiriga and Virvou 2003a, b) and GIAS (Castillo et al. 2009) to model the
learner's knowledge. Moreover, Al-Hmouz et al. (2010, 2011) have applied a
hybrid student model, which combines machine-learning techniques with stereo-
types, to predict the student knowledge.
Therefore, there are a variety of student modeling techniques that can be
used or combined to model the learner's knowledge. Each one is preferred
in relation with the system's characteristics and the researchers needs. In
Table 1.1 , the percentages of preferences for each one of the student modeling
techniques for modeling the student's knowledge are presented considering the
above literature review. The information that is derived from the particular table
is the number of the adaptive educational systems that incorporate a particular
student modeling technique for the representation of the learner's knowledge
level in a set of one hundred adaptive educational systems. For example, if we
have a hundred adaptive educational systems 42.55 of them will use overlay,
29.79 will use stereotypes etc. A system can integrate more than one student
modeling techniques.

1.3.2 Errors/Misconceptions

Knowledge level is not the only the common student's characteristic that is, usu-
ally, detected and measured through questionnaires and tests. The educational sys-
tem can, also, identify the student's misconceptions and errors through these tests
as well as observing student's actions during the learning process. A student's mis-
conception is an erroneous belief, idea, thought. It is a misunderstanding that is
usually caused by incorrect thinking or faulty facts.
Many researchers of intelligent and/or adaptive educational systems have
modeled the student's errors and misconceptions in order to provide each indi-
vidual learner with personalized feedback and support. The most commonly used
approach for modeling the learner's errors and misconceptions is the perturbation
model. Many adaptive educational systems have used the particular student modeling