*****Apologies for multiple postings***** ----------------------------------------------------------------- **** NOTE: Submission Deadline is Jan. 31, 2004 **** CALL FOR PAPERS Special Issue on User Modeling and Constraint-Based Tutors User Modeling and User-Adapted Interaction: The Journal of Personalization Research (an international journal published by Kluwer) BACKGROUND: Intelligent tutoring systems offer individualized instruction by adapting to the knowledge, needs and learning abilities of their individual users. In order to be able to do so, these systems need to model the knowledge and other characteristics of their students. Many student modeling approaches have been proposed over the years, with only a few of them being used widely and outside of research labs. One such approach is constraint-based modeling, proposed by Stellan Ohlsson in early 1990s. CBM arises from Ohlsson’s theory of learning from performance errors, which proposes that we often make mistakes when performing a task, even when we have been taught the correct way to do it. According to this theory, we make mistakes because the declarative knowledge we have learned has not been internalized in our procedural knowledge, and so the number of decisions we must make while performing the procedure is sufficiently large that we make mistakes. By practicing the task, however, and catching ourselves (or being caught by a mentor) making mistakes, we modify our procedure to incorporate the appropriate rule that we have violated. Over time we internalise all of the declarative knowledge about the task, and so the number of mistakes we make is reduced. A student needs declarative knowledge in order to detect an error. If the student does not possess such declarative knowledge, an ITS may play the role of a mentor, and inform the student of the mistake. A carefully designed sequence of feedback messages, which reflects the action of a human teacher, helps the student to overcome problems in his/her knowledge. The starting point for CBM is that correct solutions are similar to each other in that they satisfy all the general principles of the domain. No correct solution can be arrived at by traversing a problem state that violates a fundamental principle of the domain. In CBM, we are not interested in what the student has done, but in what state they are currently in. Several constraint-based tutors have been developed and evaluation studies performed show that they support students’ learning and require less effort to develop compared to some other existing student modeling approaches. CALL FOR PAPERS: Papers presenting original contributions pertinent to Constraint-Based Modeling are sought for a special issue of the journal "User Modeling and User-Adapted Interaction: The Journal of Personalization Research" published by Kluwer. We solicit papers that address theoretical issues relevant to adaptation in constraint-based intelligent tutoring systems, as well as application papers that present novel implemented systems. Theoretical papers should present new techniques or enhancements of CBM, or empirical studies relevant to constraint-based tutors. Application papers should present new constraint-based systems that have been implemented and evaluated, clearly presenting the advances offered by the systems. HOW TO SUBMIT: Submissions to the special issue should follow the UMUAI submission instructions which are obtainable from the Web site http://umuai.informatikl.uni-essen.de Electronic submissions are preferred. Each submission should note that it is intended for the special issue on User Modeling and Constraint-Based Tutors. UMUAI is an archival journal that publishes mature and substantiated research results on the (dynamic) adaptation of computer systems to their human users, and the role that a model of the system about the user plays in this context. Many articles in UMUAI are quite comprehensive and describe the results of several years of work. Consequently, UMUAI gives "unlimited" space to authors (so long as what they write is important). Potential authors are asked to notify the guest editors (Tanja Mitrovic, email: [log in to unmask]) as soon as possible of their intent to submit an article. Sometime thereafter (but preferably a month prior to the submission deadline), they should submit a tentative title and short abstract (which can be altered for the actual submission) to assist in the formation of a panel of appropriate reviewers. REVIEW PROCESS: Submissions will undergo the normal review process, and will be reviewed by three established researchers selected from a panel of reviewers formed for the special issue. Barring unforeseen problems, authors can expect to be notified regarding the review results within three months of submission. IMPORTANT DATES: Notification of Intent to Submit: as soon as possible Deadline Date for Submissions: January 31, 2004 Please address any questions to the guest editor: Tanja Mitrovic Computer Science Department University of Canterbury Christchurch, New Zealand http://www.cosc.canterbury.ac.nz/~tanja Phone: +64 3 3642987 ext 7771 Fax: +64 3 3642569 Email: [log in to unmask]