Appendix F 22 May 11-50 Reasoning at AtGentSchool (Ontdeknet).ppt
Download
Report
Transcript Appendix F 22 May 11-50 Reasoning at AtGentSchool (Ontdeknet).ppt
Reasoning in AtgentSchool
From conceptual framework to implementation
Events reasoning intervention
Koen Molenaar – David Kingma
Oxford, 22-5-2005
Contribution – WP1
Deliverable 1.1:
Descriptions of Ontdeknet
Cases of usages within Ontdeknet
English version Ontdeknet
Deliverable 1.2:
Intervention model in the learning proces
(Regulate, cognitive, meta-cognitive)
Cognitive load theory
Attention & Motivation
Contribution – WP2
Deliverable 2.1:
WOZ – insights in events
Clarifying relation general and specific components
Deliverable 2.2:
Analysis of events – interventions within Ontdeknet
Relation conceptual framework – Ontdeknet
Deliverable 2.3
Set up a general intervention model for Ontdeknet
Validation intervention model with WOz
Deliverable 2.4
Experiences implementing conceptual framework events
Contribution – WP*
WP3 Deliverable 3.1:
Implementation conceptual framework events in Ontdeknet
WP4 Deliverable 4.1:
WOZ – formative evaluation setup.
WP5
Czech version Ontdeknet
Teacher presentation Ontdeknet
WP6
Atgentive on national seminars
WP7
WP3 Kick off – contributions, tasks and planning
What did we do?
App lication
(Ontdeknet, ICDT)
….
User
Propos e
interven tion
user's activity
in application
environment
Retrieve
possible
alternative
focus
Select time
and mo de of
presentation
Atgentive agents
Preferences
Alternative foci
User information
User model
É
Why reasoning?
We need to connect the event information to
interventions.
Asking questions to the user is:
distracting and disturbs the learning process and
user might not provide reliable information.
Adapt to the amount of available data, which
depends on the application / environment.
Allowing the atgentive module to adapt the
application to the user.
Been there, done that
Lots of theory available on reasoning, using:
Rules
Agents
Decision trees
Neural networks
….
So what’s the problem?
The Atgentive < > application interface is
unclear
All applications are different and thus have
different kinds of data available
Do we need planning for automated metacognitive support?
Can we parameterize all the needed
information?
A few examples
Which external event is important to the user,
and when should we notify him?
How to decide on the modality of the
interaction?
Limited resources available, how to decide if
and what other task to propose?
When to re-attract an idle-user attention (when
is a user idle?)
Information available
A standalone Atgentive module cannot cope
with all the information available from the
application.
For example:
Cognitive load of the user.
Planning of the user and other resources
needed for certain tasks
Actions of the application
Information available (II)
Should the application pre-process the data?
Should the application be able to somehow
adjust the reasoning parts in the Atgentive
module?
Should the application have the last word?
WOz
• The Wizard of Oz construction allows to:
Validate Ontdeknet events (WP4)
Validate C.F. events (WP2)
Validate intervention model (WP4)
Validate the separation between application and the
Atgentive module
Validate reasoning rules, before coding them
Collect statistical data?
More details about the WOz in the afternoon!