Intelligent tutoring system
Editor: Jacqueline Bourdeau, Télé-université, Montréal; Monique Grandbastien, Université Henri-Poincaré, Nancy
An Intelligent tutoring system (ITS) is an AI-based system that can reason upon models of knowledge useful for fostering and evaluating learning. The main function of an ITS is to adapt to the learner through an understanding or an awareness of her cognitive, meta-cognitive or affective states.
Comments on the history
The term “intelligent tutoring systems” was coined by David Sleeman and John Seely Brown (Sleeman and Brown 1982 p.1), acknowledging the evolution of Computer Assisted Instruction (CAI) into Intelligent Computer Assisted Instruction (ICAI), and emphasizing the focus on individual learning. In 1987, Wenger provided a detailed description of ITS in his seminal book entitled “Artificial Intelligence and Tutoring Systems”. In 1988 started the series of biannual ITS conferences. Most results from ITS research are to be found in the International Journal of Artificial Intelligence and Education.
Student modeling; Student model; Learner modeling; Learner model; learner module; Knowledge representation; Knowledge model; Knowledge module; Pedagogical module; Educational data mining; Artificial Intelligence in Education.
French: système tutoriel intelligent; tuteur intelligent.
The field of ITS is by nature interdisciplinary, at the crossroads of computer science (artificial intelligence, software engineering, data mining, HCI) and educational psychology, cognitive science and instructional science. ITS research challenges these fields both at the fundamental and the methodological levels, and stimulates interdisciplinary thinking. From its origin, it represents an important milestone in the structuration of research on AI and Learning. Characteristics of ITS research is the emphasis on individualization and the requirement for the system to have its own problem solving expertise, as well as specific tutoring to conduct its interaction with the student: “Computer-assisted instruction evolves toward intelligent tutoring systems (ITSs) by passing three tests on intelligence. First, the subject matter, or domain, must be “known” to the computer system well enough for this embedded expert to draw inferences or solve problems in the domain. Second, the system must be able to deduce learners’ approximation of that knowledge. Third the tutorial strategy or pedagogy must be intelligent in that the “instructor in the box” can implement strategies to reduce the difference between expert and student performance.” (Burns and Capps, p.1). This is translated into the classical three modules architecture of ITSs: the domain module, the tutor module and the learner module. Following John Self (1999, p.350), basic architecture of ITSs was already established in the mid-seventies. However, “beside this classic component view of ITSs, these systems offer a number of services. The implementation of some of these services usually transcends the individual components”, all of these aiming at fine-tuned adaptation to the learner (Nkambou et al. 2010, p.5).
 Burns H.& Capps C. (1988) Foundation of intelligent tutoring systems: an introduction. In: Polson M. C., Richardson J. J. (eds.), Foundations of Intelligent tutoring systems (pp.1-19).Hillsdale, NJ: Laurence Erlbaum.
 Nkambou R., Bourdeau J., Mizoguchi R. (eds.) (2010). Advances in Intelligent tutoring systems. Springer Verlag.
 Self J. (1999) The defining characteristics of intelligent tutoring systems research: ITSs care, precisely. International Journal of Artificial Intelligence in Education, 10, 350-364
 Sleeman D., Brown J. S. (eds) (1982) Intelligent tutoring systems. London: Academic Press.
 Wenger E. (1987) Artificial Intelligence and Tutoring Systems. Los Altos, CA: Kaufman Publishers.
 Woolf B. (2009) Building Intelligent Interactive Tutors: Student-centered Strategies for Revolutionizing E-learning. Burlington, MA, Morgan Kaufmann.