Despite Model-tracing tutors' efficiency, it is currently estimated that 1 hour of tutoring takes 200-300 hours of development . The main reason for this is the knowledge acquisition bottleneck : extracting the knowledge from the domain experts and encoding it into a program. Knowledge reuse appears as a necessity to overcome the knowledge acquisition bottleneck. Since expert knowledge and especially tutoring knowledge is so hard to create, re-using it is of paramount importance.
One widely used and quite promising technology for knowledge reuse is ontological engineering. In the case of model-tracing tutors, ontology engineering is the task of defining the cognitive model (facts, production rules) and tutoring model (user interface, model tracing and knowledge tracing) of the tutor and encode them in an ontology using specially designed environments for ontology management. This is the first research goal of the MATHESIS project. An efficient representation of all the tutor's models in an ontology will provide a search space for the problem of tutor authoring.
The second research goal is to develop the authoring tools that will help human authors search through this ontology space and therefore make their authoring faster and easier.
For the development and implementation of these research goals a bottom-up approach seems more appropriate. First, a working prototype of a model-tracing tutor will be implemented. Then, the knowledge embedded in this tutor will be used to develop an ontology. Finally, based on the ontology a suite of authoring tools will be developed. Their purpose will be to guide the search through the ontology and help human authors. (Video)
D. Sklavakis. The MATHESIS Meta-Authoring Framework for Intelligent Tutoring Systems in Mathematics. PhD Thesis, Department of Applied Informatics, University of Macedonia, Greece, 2015. ( PDF )
D. Sklavakis and I. Refanidis. The MATHESIS meta-knowledge engineering framework: Ontology-driven development of intelligent tutoring systems. Applied Ontology, Vol. 9 (3-4), pp. 237-265, 2014. ( PDF )
D. Sklavakis and I. Refanidis. MATHESIS: An Intelligent Web-Based Algebra Tutoring School. International Journal of Artificial Intelligence in Education Vol. 22, pp. 191-218, 2013. ( PDF )
D. Sklavakis and I. Refanidis. The MATHESIS Semantic Authoring Framework: Ontology-Driven Knowledge Engineering for ITS Authoring.
Proceedings of the 15th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems , Kaiserslautern, Germany, September 2011. Springer, KES 2011, Part II, LNAI 6882, pp 114-123, 2011. ( PDF ) ( PPT) ( DEMO1: Tutor and Tutoring Processes Authoring Tools) ( DEMO2: Authoring Processes Authoring Tools)
D. Sklavakis and I. Refanidis. Ontology-Based Authoring of Intelligent Model-Tracing Math Tutors. Proceedings of the 14th International Conference on Artificial Intelligence: Methodology, Systems, Applications (AIMSA 2010), Varna, Bulgaria, 8-10 September, 2010. Springer, LNAI 6304, pp 201-210, 2010. ( PDF ) ( PPT )
D. Sklavakis and I. Refanidis. MATHESIS: A Web-Based Intelligent Tutoring School for Algebra. Intelligent System Demostration at the 6th Hellenic Conference on Artificial Intelligence (SETN 2010), Athens, 4-7 May, 2010. ( DEMO ) ( PDF )
D. Sklavakis and I. Refanidis. The MATHESIS Ontology: Reusable Authoring Knowledge for Reusable Intelligent Tutors.
7th International Workshop on Ontologies and Semantic Web for E-Learning (SWEL09) in conjunction with AIED 2009, Brighton, 7th July, 2009. ( PDF ) ( PPT )
D. Sklavakis and I. Refanidis. The MATHESIS Algebra Tutor: Web-based Expert Tutoring via Deep Model Tracing. Interactive Event at the 14th International Conference on Artificial Intelligence in Education (AIED2009), Brighton, 6-10th July, 2009. ( DEMO ) ( PDF )
D. Sklavakis and I. Refanidis. An Individualized Web-based Algebra Tutor Based on Dynamic Deep Model Tracing. 5th Hellenic Conference on Artificial Intelligence, Syros, Greece. Springer. ( PDF ) ( PPT )
Aitken, J.S., and Sklavakis, D. Integrating Problem-Solving Methods into Cyc. Proceedings of the 16th International Joint Conference on Artificial Intelligence , ed. Dean, T., Stockholm, 3-6th August 1999, Morgan Kaufmann. ( PDF )
D. Sklavakis. Implementing Problem-Solving Methods in CYC. MSc Thesis, Department of Artificial Intelligence, University of Edinburgh, 1998. ( PDF )
The MATHESIS Intelligent Algebra Tutoring School (English)
The MATHESIS Tutor and Tutoring Processes Authoring Tools (Demo)
The MATHESIS Authoring Processes Authoring Tools (Demo)
ΜΑΘΗΣΙΣ: Ένας ευφυής διαδικτυακός βοηθός Άλγεβρας (Greek)
ΜΑΘΗΣΙΣ: Μία ευφυής διαδικτυακή τάξη Άλγεβρας (Greek)
The MATHESIS Ontology