An Open and Inspectable Learner Modeling with a Negotiation Mechanism to Solve Cognitive Conflicts...
-
Upload
jonathas-magalhaes -
Category
Technology
-
view
170 -
download
1
description
Transcript of An Open and Inspectable Learner Modeling with a Negotiation Mechanism to Solve Cognitive Conflicts...
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
An Open and Inspectable Learner Modeling with aNegotiation Mechanism to Solve Cognitive Conflicts
in an Intelligent Tutoring System
Evandro Costa, Priscylla Silva,Jonathas Magalhaes and Marlos Silva
TIPS GroupComputing Institute
Federal University of Alagoas, BrazilFederal University of Campina Grande, Brazil
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 1
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Research Context
Learner modeling tasks in ITS;
High level of uncertainty;
Probabilistic Learner Modeling in ITS;
Opening and Viewing Learner Model;
Presence of Cognitive Conflicts;
Mechanisms for dealing with conflicts;
Negotiating the open learner model.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 2
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Research Questions
Q1: What approach should we adopt to deal with uncertaintyfound in a learner model for ITS?
Q2: What is an appropriate way to define and viewing OLM?
Q3: How can we detect cognitive conflicts between the studentand the system concerning problem solving activities?
Q4: How can we effectively address these conflicts?
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 3
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
How those Questions have been addressed?
With respect to Q1 – Representation and Maintenance:
Conati et al. [2];
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 4
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
How those Questions have been addressed?
With respect to Q2 – OLM and Visualization:
Zapata and Greer [5];
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 5
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
How those Questions have been addressed?
With respect to Q3 and Q4 – Conflicts detection and Negotiation:
Bull et al. [1];
Dimitrova [3];
Thomson and Mitrovic [4].
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 6
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Our General Approach
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 7
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
The Open Learner Model
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 8
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
The Open Learner Model
The system put a problem to the learner: 13 + 4
3 ;
He declares his belief:
Very unsure = 0.05;Unsure = 0.25;Almost sure = 0.5;Sure = 0.75;Very sure = 0.95.
Then, he submits a solution and the system evaluate it andreturns a grade [0,1].
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 9
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
The Open Learner Model
(a) The Ms . (b) The Mt .
Figure: Task-specific part of the Learner Model.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 10
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
The Open Learner Model
(a) The Ms . (b) The Mt .
Figure: Domain-general part of the Learner Model.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 11
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
The Open Learner Model
Figure: The Visualization of the Learner Model.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 12
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Negotiation Process
The negotiation mechanism depends on the learner’s credibility:
Figure: The DBN of the learner’s credibility.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 13
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Negotiation Process
When the learner wants to change the tutor’s belief
Credibility L’s belief < T’s belief L’s Belief > T’s beliefLow Persuasion Persuasion
Medium Persuasion CooperationHigh Persuasion Cooperation
When the tutor wants to change the student’s belief
Credibility L’s belief < T’s belief L’s belief > T’s beliefLow Support Contestation
Medium Support ContestationHigh Support Contestation
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 14
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Prove Process
During the negotiation:
The system can request that the learner proves his knowledge, or;The learner can request the opportunity of prove.
The proof process consists of:
Two problems and the learner has two chances to solve eachproblem;Then, his model is updated.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 15
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Demonstration Scenario
Figure: Example of Negotiation Dialogue Started by the Learner.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 16
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
We are we going next?
Improve the visualization, allowing the visualization of the twoparts of the model;
Put other evidences in the learner model: social characteristics,CV-curriculum of the student, collaborative information;
Perform an experiment in a basic math classroom.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 17
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
References
Susan Bull, Paul Brna, and Helen Pain.Extending the scope of the student model.User Modeling and User-Adapted Interaction, 5(1):45–65, 1995.
Cristina Conati, Abigail Gertner, and Kurt Vanlehn.Using bayesian networks to manage uncertainty in studentmodeling.User Modeling and User-Adapted Interaction, 12(4):371–417,2002.
Vania Dimitrova.Style-olm: Interactive open learner modelling.International Journal of Artificial Intelligence in Education,13(1):35–78, January 2003.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 18
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Referencias
David Thomson and Antonija Mitrovic.Preliminary evaluation of a negotiable student model in aconstraint-based its.Research and Practice in Technology Enhanced Learning,5(1):19–33, 2010.
Juan-Diego Zapata-Rivera and Jim E. Greer.Interacting with inspectable bayesian student models.International Journal of Artificial Intelligence in Education,14(2):127–163, 2004.
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 19
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
Thanks!!
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 20
IntroductionRelated WorkOur Proposal
Demonstration ScenarioFinal Considerations
References
For more information: http://tip.ic.ufal.br/site/
E. Costa, P. Silva, J. Magalhaes and M. Silva PALE UMAP 2012 21