Student Modeling for Personalized Education: A Review of the Literature - Advances in Personalized Web-Based Education - page 18

Table 1.3 Student modeling approaches in relation to student's learning style and preferences
Overlay

Stereotypes Fuzzy

techniques

Cognitive
theories

Machine
learning
techniques

Bayesian
networks

Ontologies

13.64 % 31.82 % 22.73 % 4.55 % 13.64 % 22.73 % 4.55 %

Learning
styles and
preferences

mastery, her/his cognitive characteristics by combining overlay with stereotypes
and fuzzy techniques. Also, Mahnane et al. (2012) have used stereotypes to inte-
grate thinking style (AHS-TS) in an adaptive hypermedia system. In addition,
Wang et al. (2009) have built a student model, which is based on machine learning
techniques and represents the learner's language competence, cognitive character-
istics and learning preferences, in order to assist students in successfully mastering
the English language. Other researchers that have modeled the cognitive char-
acteristics of students are: Jurado et al. (2008), who have used machine learning
techniques in combination with fuzzy techniques; Al-Hmouz et al. (2010, 2011),
who have combined stereotypes with machine learning techniques, and Viccari
et al. (2008), who have built a student model based on cognitive theories and
Bayesian networks.
Therefore, there are a variety of student modeling techniques that can be
used to model the learner's cognitive features. In Table 1.3 , the percentages of
preferences for each one of the student modeling techniques for modeling the
student's learning styles and preferences are presented considering the above
literature review. Furthermore, in Table 1.4 , the percentages of preferences for
each one of the student modeling techniques for modeling the student's general
cognitive features other than knowledge (including learning styles and prefer-
ences) are presented considering the above literature review. The information
that is derived from the above tables is the number of the adaptive educational
systems that incorporate a particular student modeling technique for modeling
the student's learning style, preferences and other cognitive features in a set
of one hundred adaptive educational systems. From the data on the tables, it is
concluded that stereotypes is the most popular student modeling technique for
representing the student's learning styles and other cognitive features (other than
knowledge).

Table 1.4 Student modeling approaches in relation to student's cognitive features other than
knowledge

Overlay Stereotypes Fuzzy

techniques

Cognitive
theories

Machine
learning
techniques

Bayesian
networks

Ontologies

8.33 % 38.89 % 22.22 % 5.56 % 19.44 % 22.22 % 8.33 %

Cognitive
f eatures other
than knowledge