|
|
|
Student Modeling
•One
of the components in an ITS.
•Used
to predict what the student might do next & to serve as a
repository of past student solutions.
•Helps
direct students to unknown materials when concepts are
mastered & to materials that needs to be reviewed when
student is unsure.
•Stores
specific information of each individual learner.
•Should
at least be able to track how well a student is
doing on a particular material.
•Provides
data for the Pedagogical Module of the ITS.
A student model
includes information about a certain student's knowledge level, skills level, tasks
performance ability, psychological and other characteristics like
learning styles and interaction styles.
Click to download
paper
Pierre Dillenbourg
and John Self
Presents a
conceptual framework and notation for learner modeling in
ITS. It is based on the computational distinction
between behavior, behavioral knowledge and conceptual
knowledge.
Click to download
paper
Susan
Bull
A survey that supports Open
Learner Model in intelligent learning environments. The paper
present several OLM: Inspectable, Co-operative, Editable,
Negotiated, System-initiated, Learner-initiated and
mixed-initiative.
Click to download paper
An online tutorial
on how to build ITS by
Dr. A.
Serengul Guven Smith-Atakan
from Middlesex University. Explains the different student models
(overlay, differential and pertubations). Provide examples of
ITS and adaptive hypertext systems.
 http://www.cs.mdx.ac.uk/staffpages/serengul/table.of.contents.htm
This online book
by
Prof Dr. Schulmeister
from Hamburg University, Denmark contains information about
building hypermedia learning systems. Has a section on ITS and
explains each component. There is also a link to many examples
of systems.
http://www.izhd.uni-hamburg.de/paginae/Book/Frames/Start_FRAME.html
|
•
The Open Learner Model
promotes an open environment for reflection of the
learner themselves and their peers. The student model is
generated on-the-fly as the lesson proceeds.
Click to download paper
Neural network
is used to predict student solutions and gives the
ability to answer as the student would on problems that
the network has never seen before. It can generalize the
student answers.
Click to download paper
|
|
•
Stores specific information of each
individual learner.
•Should
at least be able to track how well a student is doing on
a particular material.
•Provides
data for the Pedagogical Module of the ITS.
Must record student’s
understanding of the domain.
•To
include more general pedagogical info about the
student.
–E.g.
whether the student likes to look at examples
before attempting to answer questions.
•Acquisition
(measures how fast students learn new topics) &
Retention (measures how well they recall
material over time).
http://www.acm.org/crossroads/xrds3-1/aied.html
|
|
Peter
Brusilovsky
This paper proposes an advanced
student model for Intelligent Learning Systems; systems that have an
additional component to support ‘student-driven’ learning, the ‘environment
module’, in addition to the regular tutoring component.
The paper discusses the problems
experienced while using a simple student model (which is
effective for Intelligent Tutoring Systems) where all the
various components of the system like, the tutoring, coaching,
environment components, use the central student model to adapt
their behavior. It talks about the limitations of such a model
for an ILE and then proposes an advanced student model where
each component keeps a time-stamped record of its activity with
the student and reports it back to the central student model.
http://www.sis.pitt.edu/~peterb/papers/UM94.html
|
|
| |
|
| |
|
| |
|
|
