An Adaptive Tutor to Promote Learner’s Skills Acquisition during Procedural Learning Joanna TAOUM Workshop “eliciting Adaptive Sequences for Learning” ITS, Montréal ( Canada ) , June 2018
CONTEXT Actions and Procedures on ECA Positive Effect Pedagogical Interaction Technical Systems Communication content Student engagement Pedagogical Scenarios [Kopp et al . , 2008 ] [Rowe et al . , 2007 ] [Saunier et al . , 2016 ] Intelligent Virtual Effectiveness of teaching Environment [Kokane et al . , 2014 ] [Aylett and Cavazza, 2001 ] STEVE [Johnson, 1998 ] Windmill Structure and VE Representation 1/15 taoum@enib . fr
PROPOSITION LEARNER’S EVOLUTION Each learner evolves differently OBJECTIVE Improving ECA with an adaptive tutor behavior, that is able to adapt the execution of a pedagogical scenario according to the learning performance of a learner WHY ? To enhance learner’s learning performance 2/15 taoum@enib . fr
INTELLIGENT TUTORING SYSTEM ▰ Formalization of the intelligent virtual environment Domain Model Student Model Tutoring Model User - Interface Learner ITS four component architecture [Nkambou et al . , 2010 ] 3/15 taoum@enib . fr
INTELLIGENT TUTORING SYSTEM ▰ Domain expert knowledge Domain Model Student Model Tutoring Model User - Interface Learner ITS four component architecture [Nkambou et al . , 2010 ] 4/15 taoum@enib . fr
DOMAIN MODEL : M ASCARET ▰ Domain model is represented by M ASCARET [Chevaillier et al . , 2001 ] § Virtual Reality meta - model based on UML for designing the semantic of the IVE § Domain and pedagogical concepts are explicit Agent Knowledge Base Environment ( M ASCARET ) Users & Agents Structure activities and interaction Entities’ Behavior 4/15 taoum@enib . fr
INTELLIGENT TUTORING SYSTEM ▰ Natural realization of pedagogical actions Domain Model Student Model Tutoring Model Embodied User - Interface Conversational Learner Agent ( ECA ) ITS four component architecture [Nkambou et al . , 2010 ] 5/15 taoum@enib . fr
IINTERFACE ▰ Interface is represented by ECA S AIBA Compliant Learner Tutor ( Human user ) ( ECA ) G RETA Smiling Frowning PRIMITIVE ACTIONS [Niewiadomski et al . , 2009 ] Multi - modal Verbal communication : giving an information, … Signals Non - verbal communication : multimodal signals, … V HT [Gratch et al . , 2013 ] Actions on the environment : manipulating an object, … Pointing Navigation : observing, moving, … M ARC PEDAGOGICAL ACTIONS [Courgeon, 2011 ] On the virtual environment : highlighting an object, … In Mascaret, the tutor and the learner On the user’s interaction : changing viewpoint, … are considered as Agents On the structure of the system : describing the structure, … 5/15 taoum@enib . fr
INTERFACE 5/15 taoum@enib . fr
INTELLIGENT TUTORING SYSTEM ▰ Adaptation of the pedagogical scenario based on the learner’s knowledge Domain Model Instructions Student Model encoding Tutoring Model in memories User - Interface Learner ITS four component architecture [Nkambou et al . , 2010 ] 6/15 taoum@enib . fr
STUDENT MODEL ▰ General theoretical framework of human memory [Atkinson and Shiffrin, 1968 ] Rehearsal Storing Long - term Sensory Working Incoming Memory Memory Memory Encoding Information Retrieving ▰ Main contribution : § Formalizing the content of memory § Implementing the execution flow of memories 6/15 taoum@enib . fr
Example Visual register Visual Information Auditory Information Auditive register Open the tube of Neoplastin Encoding 7 chunks Storing Retrieval 7/15 taoum@enib . fr
Example Visual register Visual Information Auditory Information Auditive register Open the tube of Neoplastin Encoding 7 chunks Storing Retrieval 7/15 taoum@enib . fr
Example Visual register Visual Information Auditory Information Auditive register Open the tube of Neoplastin Encoding 7 chunks Storing Retrieval 7/15 taoum@enib . fr
Example Visual register Visual Information Auditory Information Auditive register Open the tube of Neoplastin Encoding 7 chunks Storing Retrieval 7/15 taoum@enib . fr
Example Visual register Visual Information Auditory Information Auditive register Encoding 7 chunks Storing Retrieval 7/15 taoum@enib . fr
INTELLIGENT TUTORING SYSTEM ▰ Adaptive tutor behavior based on Domain and Student Model Domain Model Adaptive Tutor Student Model Tutoring Model Behavior User - Interface Learner ITS four component architecture [Nkambou et al . , 2010 ] 8/15 taoum@enib . fr
TUTOR BEHAVIOR Action Pedagogical Inputs Working Domain Long - term realization Memory scenario Model Memory Adaptive Behavior expected Long - term Memory Transfer Working Memory Remediation Modification ( Pedagogical action ) unexpected Based on cognitive psychology hypothesis. 8/15 taoum@enib . fr Behavior to be defined using UML activity diagrams.
TUTOR BEHAVIOR 8/15 taoum@enib . fr
EVALUATION Objective Evaluate the impact of our adaptive virtual tutor on the learner’s learning performance Application Procedural learning for blood analysis in a virtual environment laboratory Participants Two groups of 22 participants each, 14 % female, mean age 22 , 7 Objective Performance Measure Time, errors and Help request 9/15 taoum@enib . fr
EVALUATION Experimental Protocol Same first trial for both groups “Systematic Assistance” Group I Group II Adaptive Tutor Non - Adaptive Tutor Pedagogical actions based on the No pedagogical actions learner’s memories content One type of help request Different types of help request Feedback when incorrect action Feedback when incorrect object ( Goal + Action + Object ) and / or action and inaction taoum@enib . fr 10/15
RESULTS Statistical analysis applied starting trial 2 350 MEAN OF REALIZATION TIME 300 Realization time (sec) Significant results only 250 200 for the second trial : 150 Learner’s in adaptive 100 condition takes less time to 50 realize the procedure 0 2 3 4 5 Trial’s number taoum@enib . fr 11/15
RESULTS Statistical analysis applied starting trial 2 10 9 MEAN OF HELP REQUEST 8 Number of help request 7 Significant results for the 6 second trial and for all 5 4 trials : 3 2 In general, adaptive 1 0 condition participants 2 3 4 5 require less help Trial’s number taoum@enib . fr 12/15
RESULTS Statistical analysis applied starting trial 2 7 MEAN OF INCORRECT ACTIONS 6 Number of incorrect actions Significant results for the 5 second trial and for all 4 trials : 3 2 In general, adaptive 1 condition participants make 0 fewer incorrect actions . 2 3 4 5 Trial’s number taoum@enib . fr 13/15
DISCUSSION “ Generally, interaction with an adaptive virtual tutor improves learner’s performance Specially, during the first executions of the procedure taoum@enib . fr 14/15
CONCLUSION AND PERSPECTIVES We propose an adaptive virtual tutor based on Intelligent Tutoring Systems and Cognitive Psychology ( Theory of Human Memory ). The proposed model can also be applied in use cases of cognitive impairments, Alzheimer disease : modification of the memory flow . taoum@enib . fr 15/15
THANK YOU ! Any questions? You can contact me at taoum@enib . fr
An Adaptive Tutor to Promote Learner’s Skills Acquisition during Procedural Learning Joanna TAOUM Workshop “eliciting Adaptive Sequences for Learning” ITS, Montréal ( Canada ) , June 2018
Recommend
More recommend
