Intelligent tutoring system

From Wikipedia, the free encyclopedia

Broadly defined, an intelligent tutoring system (ITS) is any computer system that provides direct - i.e. without the intervention of human beings - customized instruction or feedback to students. ITS systems may employ a host of different technologies. However, usually such systems are more narrowly conceived of as artificial intelligence systems, more specifically expert systems used for tutoring. ITS systems have been around since the late 1970s, but increased in popularity in the 1990s.

ITS systems consist of four different subsystems called models or modules: the expert model or domain model, the student model, and the tutor model. The expert or domain model contains a description of the knowledge or behaviors of the expert. An example would be the kind of diagnostic and subsequent corrective actions an expert technician takes when confronted with a malfunctioning thermostat. The student model contains descriptions of student knowledge or behaviors, including his or her misconceptions and knowledge gaps. An apprentice technician might, for instance, believe a thermostat also signals too high temperatures to a furnace (misconception) or might not know about thermostats that also gauge the outdoor temperature (knowledge gap). A mismatch between a student's behavior or knowledge and the expert's presumed behavior or knowledge is signalled to the ITS system, which subsequently takes corrective action. To be able to do this, it needs information about what a human tutor in such situations would do: the tutor model.

An ITS system is only as effective as the various models it relies on to adequately model expert, student and tutor knowledge and behavior. Thus, building an ITS system needs careful preparation in terms of describing the knowledge and possible behaviors of experts, students and tutors. This description needs to be done in a formal language in order that the ITS system may process the information and draw inferences in order to generate feedback or instruction. Therefore a mere description is not enough, the knowledge contained in the models should be organised and linked to an inference engine. It is through the latter's interaction with the descriptive data that tutorial feedback is generated.

All this is a substantial amount of work, even if authoring tools have become available to ease the task. This means that building an ITS system is an option only in situations in which they, in spite of their relatively high development costs, still reduce the overall costs through reducing the need for human instructors or sufficiently boosting overall productivity. Such situations occur when large groups need to be tutored simultaneously or many replicated tutoring efforts are needed. Cases in point are technical training situations such as training of military recruits and high school mathematics. One specific type of intelligent tutoring system, cognitive tutor, has been incorporated into mathematics curricula in a substantial number of United States high schools, producing replicable gains on student performance on the SAT standardized exam. Intelligent tutoring systems have been constructed to help students learn geography, circuits, computer programming, and medical diagnosis.

The Intelligent Tutoring Systems conference was typically held every other year in Montreal at the University of Montreal in Canada by Claude Frasson in 1998, 1992 1996 and 2000 and will again be in 2008. The ITS conference was held in San Antin o in 1998, Brazil in 2004, and Tiawan in 2006. The International Artificial Intelligence in Education (AIED) Society (http://aied.inf.ed.ac.uk/aiedsoc.html) publishes The International Journal of Artificial Intelligence in Education (IJAIED) and produces the International Conference on Artificial Intelligence in Education every odd numbered year. The American Association of Artificial Intelligence (AAAI)(www.aaai.org) sometimes has symposium and papers related to ITSs. A number of books have been written on ITS including three published by Lawrence Erlbaum Associates in New Jersey.