Sp issue: computational intelligence in web-based education.

GUEST EDITORS: ATHANASIOS (THANOS) VASILAKOS, GREECE; VLADAN DEVEDZIC, SERBIA; KINSHUK, NEW ZEALAND; WITOLD PEDRYCZ, CANADA.

Educational applications on the World Wide Web (WWW or Web), publication of educational material on the Web, and other ways of using the Web as an infrastructure for learning are abundant today. Applications range from rather simple, providing little interaction or customization for students, to sophisticated intelligent web-based systems that ensure the personalization of the learning process, rich interaction between the application and the learners, as well as effective collaboration among the learners.

Generally, there are two different but overlapping aspects of web-based education: content transmission (to deliver instruction), and support for communication between teachers and learners, or among learners. The former comprises mediation of the lecturing process by complementing or replacing the traditional role of printed materials and instructors. The latter enables extending faculty availability beyond class times and office hours, establishing links to other classmates, supporting peer interaction, evaluation, and cooperation, maintaining online learning communities, and accomplishing administrative activities such as the distribution of materials, reminders, and notifications.

Recent years have witnessed a number of technologies becoming increasingly important for web-based education--network communication, information databases, multimedia applications, and virtual reality. Many of them have inevitably brought increased intelligence of educational applications. They have also spawned a number of research challenges and important questions, such as:

* How can we increase interactivity on the Web?

* How can we overcome delays due to downloading?

* Where will the intelligence be located? On the client? The server? A mix of both?

* What kind of intelligence can be used? Can we build systems as smart as our standalone systems?

* What type of connectivity and communication is possible between intelligent educational systems?

* How can the Web help (or hurt) collaborative learning efforts?

* What do we gain by using the Web in education? What do we lose?

This special issue addresses these questions from the perspective of yet another important category of technologies, collectively known as computational intelligence. Computational Intelligence (Soft Computing) being viewed as a vital synergy between fuzzy sets, neural networks, and evolutionary optimization, can play a primordial role in the development of these educational and technological challenges. Some recent applications have pointed out the potential of Computational Intelligence in the area of intelligent web-based education.

The articles in this special issue cover a whole range of interesting and important topics. Vasilakos, Devedzic, Kinshuk, and Pedrycz present an in depth tutorial for Computational Intelligence (CI) (1) technologies for web-based education (i.e., Neural Networks, Fuzzy Logic, Genetic Algorithms). Dicheva and Dichev present a general framework for building concept-based digital course libraries. The framework is based on the idea of using a conceptual structure that represents a subject domain ontology for classification of the course library content. Mitrovic, Suraweera, Martin, and Weerasinghe discuss their experiences with three web-based intelligent tutoring systems in the area of databases. SQL-Tutor teaches the SQL query language, NORMIT is a data normalization tutor, and KERMIT teaches conceptual database modeling using the Entity-Relationship data model. All three tutors in DB-suite have been used and evaluated in the context of genuine teaching activities. Chorfi and Jemni analyze design and development of an adaptive hypermedia e-learning system, called PERSO, where learners with different learning goals and different learning aptitudes are treated differently, by building a model of knowledge and preferences about each of them. This model is used to propose to the learner a personalized course fitting his or her needs. Two types of adaptation are considered: adaptive content and adaptive presentation. Karampiperis and Sampson present a learning object selection and sequencing that mimics the way an expert decides on the selection problem. Aroyo and Mizoguchi present a meta-level Authoring Task Ontology (ATO) specifying authoring tasks, goals, and activities for Intelligent Educational Systems (IES). Merceron and Yacef present a methodology for data mining to gain insight on the student's learning and deduce information to improve teaching.

(1) Pedrycz, W., & Vasilakos, A. (2000). Computational intelligence in telecommunications networks. Boca Raton, FL: CRC Press.