Generating task-specific next-step hints using domain-independent structures

Authors:
Luc Paquette;Jean-François Lebeau;Jean Pierre Mbungira;André Mayers
Affiliations:
Université de Sherbrooke, Québec, Canada;Université de Sherbrooke, Québec, Canada;Université de Sherbrooke, Québec, Canada;Université de Sherbrooke, Québec, Canada
Venue:
AIED'11 Proceedings of the 15th international conference on Artificial intelligence in education
Year:
2011

Citing 2
Cited 2

An authoring language as a key to usability in a problem-solving ITS framework

ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part II
Integrating sophisticated domain-independent pedagogical behaviors in an ITS framework

ITS'10 Proceedings of the 10th international conference on Intelligent Tutoring Systems - Volume Part II

Automating next-step hints generation using ASTUS

ITS'12 Proceedings of the 11th international conference on Intelligent Tutoring Systems
Experimental Evaluation of Automatic Hint Generation for a Logic Tutor

International Journal of Artificial Intelligence in Education - Best of AIED 2011

Quantified Score

Hi-index	0.01

Visualization

Abstract

With the ASTUS framework, our aim is to facilitate the creation of tutors showing sophisticated pedagogical behaviors while keeping the authoring effort in line with that required by other well-known frameworks. ASTUS is thus based on knowledge structures that can be manipulated by the tutor's modules in order to, for example, generate task-specific next-step hints. An experiment suggests that the generated hints can be as effective and as well appreciated as those authored by a teacher.