An Explanation Tool to Support Learning of Basic Programming

Volume LXXVIII, BAM 1196/96, pp 183-192., 1996

The activity of explaining has been studied and modeled by Artificial Intelligence researchers for almost three decades. While no standalone educational applications have resulted, a number of techniques have been developed that, when combined in the right way, can support automated explanation facilities capable of playing a useful role as one educational resource among others. In this paper, we will briefly survey the available techniques and evaluate their utility in generating explanations, and how we realized the explanation properties and features in Intelligent Tutoring System shell called EduSof. Devedžić, V. and Jerinić, Lj., Explanation In Intelligent Tutoring Systems. Bulletins for Applied Mathematics, BAM 1196/96 (LXXVIII), (May, 1996) Budapest, 183-192. Bulletins for Applied Mathematics. 01/05/1995; Volume LXXVIII, BAM 1196/96, pp 183-192.

Proceedings of the Fifteenth IASTED International Conference "Applied Informatics", 1997

The activity of explaining has been studied and modeled by Artificial Intelligence researchers for almost three decades. While no standalone educational applications have resulted, a number of techniques have been developed that, when combined in the right way, can support automated explanation facilities capable of playing a useful role as an educational resource among others. In this paper, we will briefly survey the available techniques and evaluate their utility in generating explanations, and how we realized the explanation properties and features in Intelligent Tutoring System shell called EduSof. Jerinić, Lj. and Lomić M., Explanation Module In An Intelligent Tutoring Shell. In M. H. Hamza (Ed) Proceedings of the Fifteenth IASTED International Conference "Applied Informatics" (19th - 22th February, Innsbruck, Austria). IASTED - ACTA PRESS, Zurich, 1997, pp. 294-297.""

2015 ASEE Annual Conference and Exposition Proceedings

Many research reports have been published over the last 30 years on the use of intelligent tutoring systems in computer science and software engineering education, but no previous systematic review has been conducted to describe and assess the field as a whole. This project (in progress) searched for publications meeting defined inclusion criteria and identified 280 eligible reports. We are currently coding these works using 28 variables that will allow us to describe the research field in aggregate. The results will tell us: What research questions are being asked? What are the types of student modeling being used? What subject domains have ITS been designed for? What issues or themes are most evident in recent research? What are the gaps in research on intelligent tutoring systems in computer science and software engineering education. Finally, what technological and pedagogical innovations are needed to advance research in this field? Research on intelligent tutoring systems (ITS) has accelerated over the last decade, and scholarly interest in such systems has never been greater. 1 ITS have been developed for a wide range of subject domains (e.g., mathematics, physics, biology, medicine, reading, languages, and philosophy) and for students in primary, secondary and postsecondary levels of education. Although most ITS have been developed by researchers and never deployed outside the laboratory or the single university-level course for which they were designed, there are examples of mature systems that have been deployed more widely and extensively evaluated. 2, 3 Like previous reviewers 1, 4, 5 we have adopted a definition of ITS that emphasizes student modeling as an essential characteristic. We identify an ITS as any computer system that performs teaching or tutoring functions (e.g., selecting assignments, asking questions, giving hints, evaluating responses, providing feedback, prompting reflection, providing comments that boost student interest) and adapts or personalizes those functions by modeling students' cognitive, motivational or emotional states. This definition distinguishes ITS from test-and-branch tutorial systems which individualize instruction by matching a student's most recent response against preprogrammed, question-specific targets. Complicating matters, there are sophisticated

The paper discusses the issue of generating explanations in intelligent tutoring systems. Specifically, it shows how explanations are generated according to the GET-BITS model of intelligent tutoring systems. The major concern is what software components are needed in order to generate meaningful explanations to different classes of the end-users of such systems. The process of explanation is considered in the context of the types of knowledge present in the knowledge base of an intelligent tutoring system. Throughout the paper, the process of explanation generation is treated from the software engineering point of view. Some design examples, describing several classes developed in support of explanation generation based on the GET-BITS model, are also presented.

Proceedings of 7th International Conference "Informatics in Education and New Information Technologies", 1997

"In this paper an overview of using of EduSof system (shell framework for realization of intelligent tutoring system) in designing of intelligent tutor for learning of basic programming is given. The aim in realization of LesPas system, intelligent tutor realized by using EduSof shell, is to help beginners in programming in solution defining, learning language construction while using adequate examples, as well as in implementation and testing of his own programs. Intelligent tutoring system LesPas does not only give reports on syntax, semantic and conceptual user errors. It also tries to understand users point of view while designing solution of given problem, to help, to give advice and accept original ideas, i.e. self learning is possible. Intercode representation of knowledge of basic programming enables pupil to direst creation of his solution. One mental model is given, the way of thinking, for better problem solving in basic programming. Lomić, M., Jerinić, Lj. Devedžić, V. and Radović D., Knowledge Representation in Intelligent Tutoring for the First Course for Learning of Programming. In Đ Nadrljanski and D. Lipovac (Eds.) Proceedings of 7th International Conference "Informatics in Education and New Information Technologies" (7th - 8th November, Novi Sad, Yugoslavia). Printing-house of Executive Council of Vojvodina, Novi Sad, 1997, pp. 110-115. "

researchgate.net, 1999

The difficulty of designing and developing intelligent tutoring systems (ITSs) has caused a recent increase in the interest of the AI researchers in realization of some new approaches in that field. Issues of pragmatics and usability motivate our starting point and perspective on developing of ITSs tool called GET-BITS. Considering commercially available and widely used authoring systems for traditional computer-based teaching, we try to give the next step, the next paradigm shift that is needed to enable some of the ITSs advantages. It was developed while trying to redesign a previously developed ITSs called EduSof. The model enables the developing of more flexible software environment for building of the ITSs, significantly increasing their reusability, and the model can be easily extended to cover the needs of particular tutoring systems. In this paper an overview of using the GET-BITS model in designing of ITSs for learning of basic programming is given. The aim in realization of LeaPas system, intelligent tutor realized by using EduSof shell, is to help beginners in programming in solution defining, learning language construction while using adequate examples, as well as in implementation and testing of his own programs. Intelligent tutoring system LeaPas does not only give reports on syntax, semantic and conceptual user errors. It also tries to understand users point of view while designing solution of given problem, to help, to give advice and accept original ideas, i.e. self-learning is possible. Inter-code representation of knowledge of basic programming enables pupil to direst creation of his solution. One mental model is given, the way of thinking, for better problem solving in basic programming.

1989

Abstract Providing coherent explanations of domain knowledge is essential for a fully functioning Intelligent Tutoring System (ITS). Current ITSs that generate explanations from the underlying representation provide a limited solution because they place restrictions on the form and extent of the underlying knowledge. However, generating explanations in tutors that are designed to teach the kind of foundational knowledge conveyed in most introductory college courses poses special problems.

1993

We have defined an object-oriented software architecture for Intelligent Tutoring Systems (ITSs) 2 to facilitate the rapid development, testing, and fielding of ITSs. This software architecture partitions the functionality of the ITS into a collection of software components with well-defined interfaces and execution concept. The architecture was designed to isolate advanced technology components, partition domain dependencies, take advantage of the increased availability of commercial software packages, and reduce the risks involved in acquiring ITSs. A key component of the architecture, the Executive, is a publish and subscribe message handling component that coordinates all communication between ITS components. We implemented critical components of the architecture as a simple hypermedia training system, the Macintosh Maintenance Training System (MMTS). The domain for the prototype training system is the maintenance of Apple Macintosh Ilex computers. This project has shown that the use of a modular software architecture for the development of ITSs, and complex integrated artificial intelligence applications in general, has several important benefits. Its use allows for rapid development, ' incremental integration and testing of components, and a more maintainable, extensible, and reusable end-product. Even more evident was the benefit of an Executive component that facilitated the integration of commercial software packages with custom developed software in a well-defined manner.

The paper discusses the issue of generating explanations in intelligent tutoring systems. Specifically, it shows how explanations are generated according to the GET-BITS model of intelligent tutoring systems. The major concern is what software components are needed in order to generate meaningful explanations to different classes of the end-users of such systems. The process of explanation is considered in the context of the types of knowledge present in the knowledge base of an intelligent tutoring system. Throughout the paper, the process of explanation generation is treated from the software engineering point of view. Some design examples, describing several classes developed in support of explanation generation based on the GET-BITS model, are also presented.

2004 Annual Conference Proceedings

We present the architecture of an Intelligent Interactive Tutoring System (IITS) that is webbased, and can be adapted to courses in engineering, sciences, and mathematics. This research seeks an architecture that can be used by an instructor to make an online learning system for a course the instructor wants to teach in classroom or online, rather than developing an in-depth tutoring system for any specific course. The Intelligent Interactive Tutoring System Shell integrates mathematical tools and an expert-system-type logical analysis/synthesis tool in a webbased environment. The IITS consists of several components including an instructor interface, a student interface, a student model, a student log, a reasoning system, and a mathematical tool interface module, and guides the student through a monitored problem solving session.