Showing papers on "Intelligent tutoring system published in 2001"

Cognitive Computer Tutors: Solving the Two-Sigma Problem

Abstract: Individual human tutoring is the most effective and most expensive form of instruction. Students working with individual human tutors reach achievement levels as much as two standard deviations higher than students in conventional instruction (that is, 50% of tutored students score higher than 98% of the comparison group). Two early 20th-century innovations attempted to offer benefits of individualized instruction on a broader basis: (1) mechanized individualized feedback (via teaching machines and computers) and (2) mastery learning (individualized pacing of instruction). On average each of these innovations yields about a half standard deviation achievement effect. More recently, cognitive computer tutors have implemented these innovations in the context of a cognitive model of problem solving. This paper examines the achievement effect size of these two types of student-adapted instruction in a cognitive programming tutor. Results suggest that cognitive tutors have closed the gap with and arguably surpass human tutors.

Optimising ITS Behaviour with Bayesian Networks and Decision Theory

Abstract: We propose and demonstrate a methodology for building tractable normative intelligent tutoring systems (ITSs). A normative ITS uses a Bayesian network for long-term student modelling and decision theory to select the next tutorial action. Because normative theories are a general framework for rational behaviour, they can be used to both define and apply learning theories in a rational, and therefore optimal, way. This contrasts to the more traditional approach of using an ad-hoc scheme to implement the learning theory. A key step of the methodology is the induction and the continual adaptation of the Bayesian network student model from student performance data, a step that is distinct from other recent Bayesian net approaches in which the network structure and probabilities are either chosen beforehand by an expert, or by efficiency considerations. The methodology is demonstrated by a description and evaluation of CAPIT, a normative constraint-based tutor for English capitalisation and punctuation. Our evaluation results show that a class using the full normative version of CAPIT learned the domain rules at a faster rate than the class that used a non-normative version of the same system.

Intelligent tutoring system

Abstract: A computer implemented method and apparatus for simulating an intelligent tutor for interactive adaptive training of learners in any domain includes a Domain Module, a Tutor Module and an Interface. Items to be learned, and their prerequisite and other dependency relationships are represented in a fuzzy graph, together with a fuzzy logic computational engine, which dynamically adapts the available sequence of training actions (such as presentations/explanations, simulations, exercises and tasks/questions) to a current assessment of the learner's knowledge skill, the level of difficulty of the presented material, and preferences and learning style of the individual learner. Fuzzy logic is used as the basis of arc weightings, and the computations, but the general methodology is applicable to other approaches to weighting in computation.

Constraint-Based Tutors: A Success Story

Abstract: Student modeling (SM) is recognized as one of the central problems in the area of Intelligent Tutoring Systems. Numerous SM approaches have been proposed and used with more or less success. Constraint-based modeling is a new approach, which has been used successfully in three tutors developed in our group. The approach is extremely efficient, and it overcomes many problems that other student modelling approaches suffer from. We present the advantages of CBM over other similar approaches, describe three constraint-based tutors and present our future research plans.

Designing Intelligent Tutoring Systems: A Bayesian Approach.

Abstract: This paper proposes a model and an architecture for designing intelligent tutoring system using Bayesian Networks. The design model of an intelligent tutoring system is directed towards the separation between the domain knowledge and the tutor shell. The architecture is composed by a user model, a knowledge base, an adaptation module, a pedagogical module and a presentation module. Bayesian Networks are used to assess user’s state of knowledge and preferences, in order to suggest pedagogical options and recommend future steps in the tutor. The proposed architecture is implemented in the Internet, enabling its use as an e-learning tool. An example of an intelligent tutoring system is shown for illustration purposes.

Intelligent Virtual Agents for Education and Training: Opportunities and Challenges

Abstract: Interactive virtual worlds provide a powerful medium for experiential learning. Intelligent virtual agents can cohabit virtual worlds with people and facilitate such learning as guides, mentors, and teammates. This paper reviews the main pedagogical advantages of animated agents in virtual worlds, discusses two key research challenges, and outlines an ambitious new project addressing those challenge.

ALEKS: a Web-based intelligent tutoring system

Abstract: An intelligent tutoring system is able to diagnose and adapt to a student's developing knowledge and skills, to provide precise feedback when mistakes are made or the student becomes stymied, and to present new topics when the student is ready to learn. ALEKS (Assessment and Learning in Knowledge Spaces) is an example of one such system currently used for the assessment and learning of factual knowledge in arithmetic and algebra. The terms "assessment" and "learning" will be clarified later in this paper. A web-based system, in contrast to compact-disk-based, can easily be used for the monitoring and management of entire courses and even institutions. It is very inexpensive - no college site-licensing is required - only an access code purchased by the student for a nominal fee. As an intelligent tutor, this system "teaches" the student, and provides a new and engaging way for students to learn or review the fundamentals of arithmetic and algebra. The program discussed in this article was developed with support from the National Science Foundation by ALEKS Corporation, a Delaware company formed in 1996. 1. ALEKS BACKGROUND Intelligent tutoring systems are part of a new breed of instructional computer programs made possible through recent developments in computer memory and computational speed capabilities, new computer programming languages, and in research in human cognition and learning. Through expert system technology and artificial intelligence, they are able to carry on intelligent "dialogues" with students and flexibly adjust to the knowledge and skill level of individuals, as well as provide a variety of methods of representing and accessing information. They are able to make inferences about a student's current state of knowledge and based on that knowledge, provide a choice of topics that the student is ready to learn. Some systems are oriented to discovery learning, others are more didactic, or "teaching", oriented. Compared to earlier computer-assisted instructional tools, they are far more adaptive to individual students, and better matched with current goals in mathematics education. Intelligent tutoring systems have four basic components: expert knowledge, learner modeling, tutorial planning, and communication [1]. These divisions into components are abstract and do not necessarily reflect actual separations in the physical structure of a system. The expert knowledge component consists of the facts and ideas of the particular subject to be learned, what a specialist or "expert" in the subject would know. Often this is known in various forms (in math, say, in numerical, symbolic, or graphic form). The more the expert system component is able to represent these various forms, the better it represents real human capabilities. The learner modeling component consists of the system's ability to diagnose, in an ongoing, adaptive way, the developing knowledge and skill of the student. The tutorial planning component guides the student by presenting appropriate learning activities, providing feedback in cases of mistakes or a standstill in progress, encouraging successes, determining progress, and individually-tailoring review topics. The tutorial planning component works closely with the results of the learner modeling component. Lastly, the communication component interacts with the student through words or graphical interfaces, providing the overt "intelligence" and user-friendliness evident when using an intelligent tutoring system [1]. This part may also often include the ability of the student and the instructor themselves to communicate with each other, through built-in e-mail-like capabilities. This last feature makes online intelligent tutoring systems useful for web-based courses and distance-learning. National-Louis University students represent a very diverse community of cultural backgrounds, academic abilities, ages and especially in their limited historical access to higher education. …

AutoTutor: Incorporating Back-Channel Feedback and Other Human-Like Conversational Behaviors into an Intelligent Tutoring System

Abstract: This paper describes our recent attempts to incorporate human-like conversational behaviors into the dialog moves delivered by an animated pedagogical agent that simulates human tutors. We first present a brief overview of the modules comprising AutoTutor, an intelligent tutoring system. The second section describes a set of conversational behaviors that are being incorporated into AutoTutor. The behaviors of interest involve variations in intonation, head movements, arm and hand movements, facial expressions, eye blinking, gaze direction, and back-channel feedback. The final section presents a recent empirical study concerned with back-channel feedback events during human-to-human tutoring sessions. The back-channel feedback events emitted by tutors are mostly positive (63%), mostly verbal (77%), and immediately follow speech-act boundaries or noun-phrase boundaries (83%). Tutors also deliver back-channelevents at a very high rate when students are emitting dialog, about 13 events per minute. Conversely, 88% of students' back-channel feedback events are head nods, and they occur at unbounded locations (63%).

"Docs 'n Drugs - The Virtual Polyclinic " An Intelligent Tutoring System for Web-Based and Case-Oriented Training in Medicine

Abstract: Since the beginning of the year 2000 medical students of the University of Ulm are working in their curriculum with the web-based and case- oriented tutoring system "Docs 'n Drugs - The Virtual Polyclinic". The system consists of different subsystems and services. One subsystem is the Training System. It is based on three models: the Tutoring Process Model, the Case Knowledge Model and the Medical Knowledge Model. They describe the tutoring process as a series of nodes and steps, depict the structure of the medical cases, and provide the medical knowledge respectively. Case knowledge and medical knowledge form the expert knowledge of the medical domain. Together with the tutoring process, they build the basis for automatic intelligent tutoring. After giving a deeper insight into the system architecture and the training case structure, an informal evaluation shows a first feedback of the learners.

Development of intelligent tutoring systems using knowledge structures

Abstract: The aim of this work is to develop a tool for teachers, without necessarily software development experience, to elaborate tutoring applications on a given domain. The teacher makes use of stored knowledge to choose the required contents so that the system automatically generates exercises. These exercises are completed and evaluated in real time, according to the student's reality, being able to mediate with the pupil to achieve the maximum session utilization. Control of the learning process is distributed among the student, the teacher, and the system. The student may choose the activities he/she likes to carry out, within a sub-group specified by the teacher, whereas the system specifies the exercise complexity, on the basis of the pupils performance. This work is grounded on knowledge re-utilization that makes use of pre-defined knowledge structures. These structures can be edited by a teacher to generate activities. These are carried out by a simulator, controlled by an expert system, that interacts with the student adjusting to the pupil's needs. Elements from both the instructionist and constructivist model were used. It was implemented for the practice of certain skills related to math in pre-school children.

A Web-based ITS controlled by a hybrid expert system

Abstract: The authors present the architecture of a Web-based intelligent tutoring system (ITS) for teaching high school teachers how to use new technologies. It offers course units covering the needs of users with different knowledge levels and characteristics. It tailors the presentation of the educational material to the users' diverse needs by using AI techniques to specify each user's model as well as to make pedagogical decisions. This is achieved via an expert system that uses a hybrid knowledge representation formalism integrating symbolic rules with neurocomputing.

Intelligent tutoring system authoring tool for manufacturing engineering education

Abstract: Intelligent tutoring systems (ITSs) have potential for making computer-based instruction moreadaptive and interactive, but development in the area of manufacturing engineering has been rare.However, recent developments in the area of ITS authoring tools may make this technology moreaccessible. The objectives of this study were to: 1) evaluate the feasibility of faculty coursedevelopment using an ITS authoring tool; and 2) evaluate the instructional effectiveness of thedeveloped courseware. An ITS authoring tool called XAIDA was used to develop a tutorial on howto use a computer numerical control (CNC) machine. This paper summarizes the results of apreliminary evaluation conducted with 25 undergraduate manufacturing engineering students. Theresults suggest that instructional development in XAIDA is feasible and quick, and that studentslearned from and enjoyed the tutorial

Human teacher in intelligent tutoring system: a forgotten entity

Abstract: Intelligent tutoring systems (ITSs) have not yet proved very successful and one major reason seems to be that research on ITSs has largely failed to recognize the role of the teacher in the ITS design process. The paper discusses an ongoing project at Massey University, which is incorporating a 'Human Teacher Model' in an ITS prototype to teach Japanese. The project identifies the teacher attributes and formulates them into a coherent teacher model. They are then applied in the prototype, which offers adaptivity to the teacher at two levels: presentation based adaptivity and navigation based adaptivity. We believe this work will substantially improve the applicability of ITSs in real academic environments.

A web-based intelligent tutoring system teaching nursing students fundamental aspects of biomedical technology

Abstract: In this paper, we present the architecture of a Web-based Intelligent Tutoring System (ITS) for distant education of nursing students in fundamental aspects of the most common medical equipment. It offers course units covering the needs of users with different knowledge levels and characteristics. It tailors the presentation of the educational material to the users' diverse needs by using AI techniques to specify each user's model as well as to make pedagogical decisions. This is achieved via an expert system that uses a hybrid knowledge representation formalism integrating symbolic rules with neurocomputing.

Intelligent tutoring: from SAKI to Byzantium

Abstract: Describes Byzantium, an intelligent tutoring system for teaching the concepts and skills of accounting. The generic design philosophy of Byzantium and its associated intelligent tutoring tools are described, together with commentary that places Byzantium in the tradition of the adaptive teaching machines and conversational tutorial systems (SAKI and CASTE) developed by Gordon Pask.

Electronic Homework on the WWW

Abstract: This paper presents the design of an Intelligent Tutoring System (ITS) MathEH, that is a coached problem solving system, also called "Electronic Homework". In describing the main modules of the system, we emphasize its novel aspects: (1). Using Constraint Logic Programming (CLP) as the domain knowledge representation and automatic reasoning mechanism. (2). A method for probability propagation in Bayesian networks to achieve two adversary requirements: exact probability computation and real-time response. (3). The design decisions about how to deploy MathEH on the WWW.

Pedagogical Agents for Web-Based Learning

Abstract: This presentation will discuss techniques for incorporating "guidebots," or animated pedagogical agents, into Web-based learning environments. Guidebots help keep learning on track; they offer students advice and guidance as appropriate in order to get the most out on-line learning experiences. Guidebots build on research in intelligent tutoring systems, but go further by engaging the learner in natural face-to-face interaction. Guidebots can stand on the side and discuss learning objectives with the learners; they also can work together with learners as teammates, and can play roles within interactive educational stories. They help bring the aesthetics of animated entertainment to interactive educational experiences. This talk will present recent developments in guidebot technology, and outline challenges for current research.

N 3 : NN Navigation Support System—Knowledge-Navigation in Hyperspace: The Sub-Symbolic Approach

Abstract: A navigation support system based on the sub-symbolic approach to decide the appropriate navigation strategy is proposed In exploring hyperspace, users often tend to be in undesirable states (eg, "get lost" and so on) To improve these undesirable states, a sophisticated hypermedia system, which can identify the user's needs and give some appropriate advice to the user in his/her exploring learning process, was constructed A hypermedia system with user-adaptive function based on an artificial neural network (NN) has been developed A supervised NN was used as a navigation strategy decision module in that system As a result of the evaluation of this system, the validation of the knowledge, which is learned by the NN, and the effectiveness of the navigation strategy, which is decided by the adaptive system, are shown Hypermedia is a tool for user-driven access to information (Schneiderman, 1989) It provides an effective learning environment, where users can acquire knowledge by exploring the hyperspace in his/her own way But, users often tend to "get lost" in the hyperspace Often there appears the phenomenon of redundant information access To improve these undesirable effects on users, many researches have been working to construct a sophisticated hypermedia system which can identify the user's interests, preferences, and needs and give some appropriate advice to the user in his/her exploring learning process In this article, a user model that represents exploring activities in hyperspace (HS) and a mechanism based on a sub-symbolic approach, to decide appropriate navigation strategies is proposed This article also shows the training procedure of the neural network (NN) and its result Adaptive hypermedia is a flexible system which infers the learning goal or the current learning state, by using the exploring history, the structural characters of the hypermedia, and so on As a result of its inference, this system changes its own performance to adapt to the user Brusilovsky classified the adaptive hypermedia systems from the point of view of the methods and techniques of adaptation (Brusilovsky, 1996) According to his paper, the methods for adaptation are of two types One is the content-level adaptation This method changes the contents of the node, which the user will refer to in the next step This type is also named the adaptive presentation system The other one is the link-level adaptation This method changes the links in the current node This is also named adaptive navigation support system The ELM-ART (Brusilovsky, 1996), which is an intelligent tutoring system, is one of the most famous adaptive presentation systems Its adaptation was based on a specific domain knowledge wit h a symbolic approach So, the generality of the adaptation mechanism and the flexibility of the functional extension of this system are not high The Adaptive HyperMan (Mathe & Chen, 1996) is one of the most famous adaptive hypermedia systems using a method of the content-level adaptation This system is an example of interactive adaptive hypermedia This system bases its adaptability on the use of an Adaptive Relevance Network, which is made of a collection of personal data This mechanism can store the users' interests The exploring characteristics of each user are acquired through conversation with him/her This system is useful for a situation in which a frequent interaction between the system and the user is needed An adaptive educational hypermedia system based on the sub-symbolic approach has been developed In cases of educational use, as the exploring aim of students is usually fixed by a teacher in advance, frequent interactions with the system may be obstacles for the free exploring learning of a student This article also describes the training procedure of the NN and its result The article is structured as follows In the next section the indicators that evaluate the users' exploring activity in hyperspace and the goal and content of each navigation strategy is described …

Intelligent Tutoring Systems: Confluence of Information Science and Cognitive Science

Abstract: The advent of Internet as a global communication medium has brought a new focus on an area of research in designing Intelligent Tutoring System (ITS) that has not been adequately considered so far. In the main, this has been due to the localised nature of most academic environments limiting the sources of information and an implicit assumption that information and knowledge are synonymous. These factors have led to overemphasis on learner modelling in the traditional ITS research, which seeks to enhance the interaction between the ITS as the provider and the learner as the consumer of knowledge, ignoring the crucial role played by the teacher in enhancing the learning in a given context. The limitations of the traditional approach become more visible when educational information is sought to be transmitted across long distances and the need for adaptation to local contexts becomes apparent. This paper argues that the human teacher, as the manager of learning, plays a vital role within the joint cognitive system consisting of the teacher, ITS, learner and learning peers. This role needs to be recognised by ITS designers by through a teacher model. It also suggests that ITS may perhaps best embody the emerging framework of Informing Science.

Adaptive Processing in a Medical Intelligent Tutoring System

Abstract: CIRCSIM-Tutor v. 3 is a dialogue-based intelligent tutoring system (ITS) that uses a uniform plan operator representation to make decisions at all levels of dialogue generation. It was designed to allow dynamic adaptation to the student at five levels of detail as the (typed) conversation progresses. In this paper we describe the studies that we used to make design decisions, including analysis of transcripts of human tutoring sessions, use of C4.5/C5.0, and user studies using an earlier version of the system. We are particularly interested in distinguishing decisions that are best made using user model information from those where recent dialogue history is the most relevant input.

A web-based intelligent approach to tutoring

Abstract: 1 Department of Electrical and Computer Engineering National University of Singapore, Corresponding Author. E-mail: ashraf@nus.edu.sg. Abstract  Many web-based tutoring environments involve tutoring using fixed sets of problems. Such environments are unable to accurately measure a student’s understanding about the subject matter. Unless a good pedagogical framework is used in the development of web-based teaching and learning systems, they may not be very useful. In this paper, we introduce a web-based intelligent tutoring system. Our tutoring system has been built on a robust framework of intelligent systems based on a three-tier Java client-server architecture and deployed in a world-wide-web environment. It comprises five components: a communications module, a pedagogical module, a student model, an expert model and the domain knowledge. This paper discusses the details of our system, which has been implemented for a particular undergraduate electrical and computer engineering course.

An intelligent tutoring system for teaching and learning Hoare logic

Abstract: Significant areas of the computer science curriculum are constantly and rapidly changing as new technologies (e.g., multimedia, WWW, Java) are adopted. This presents a challenge to our current education system: Intelligent Tutoring Systems (ITSs) for teaching and learning in Computer Science must be able to assist not only their student users but also the teachers in developing and managing courses to the best advantage of the students. We developed an ITS for teaching and learning Hoare logic. In this paper, we describe the practical use of the system in a computation theory course.

DTEx-Sys-a Web oriented intelligent tutoring system

Abstract: Distance learning systems (DLSs) are a class of important services that information infrastructures have to provide users. DLSs base their operation on information access, electronic transaction and communication services furnished by information infrastructures. Regarding the teaching process, by using DLSs new paradigms enable users to distribute educational content to support interaction among user classes (instructor-student, student-student and student-educational institution), testing, evaluation, and eventually advice in different domain knowledge areas. Classification of DLSs depends on the way these paradigms are implemented. In this paper, we concentrate on a particular DLS class, which encompass systems based on enabling Web access to otherwise classical intelligent tutoring systems-Web oriented intelligent tutoring systems. In this paper we present one such system-distributed tutor-expert system (DTEx-Sys), which has been developed for asynchronous distance educational purposes. DTEx-Sys is designed as a 3-tier client-server architecture where the intelligent tutoring functions are separated from the user interface and the knowledge base(s). The system functionality comprehends knowledge base access for arbitrary domain knowledge, along with testing, diagnosing and evaluation of students' work.

The Learning Mechanism of the Interactive Multimedia Intelligent Tutoring System (IMITS)

Abstract: The Interactive Multimedia Intelligent Tutoring System (IMITS) project integrates interactive multimedia with expert system technology. A test bed that uses material from introductory electrical circuits courses, IMITS demonstrates that these two complementary technologies may be combined successfully to form a framework useful for any educational material. IMITS combines several commercially available packages and establishes dynamic communications among these packages. This paper describes one aspect of IMITS: the learning mechanism that is controlled by the expert system and that attempts to assist the student learn the material and concepts presented.

An adapted virtual class based on intelligent tutoring system and agent approaches

Abstract: The paper describes a virtual class, which is based on the principles of ITS (intelligent tutoring systems). The virtual class allows a group of learners to participate in training sessions of an adapted teleteaching system (adapted virtual class); this system takes into account different progression rhythms in a community of remote learners. The virtual class allows adapting of the teaching system in a flexible, individual, and collective way. Agent-oriented modeling is used to specify and implement the architecture of adaptable virtual classes. The implementation of virtual class is being developed in a distance education context using reactive agents, Internet and Java.

Neural network application on knowledge acquisition for adaptive hypermedia learning

Abstract: Computers have been used in education for over 20 years. Computer-based training and computer aided instruction were the first such system deployed as an attempt to teach using computers. For a computer based educational system to provide individualized attention that a student would receive from a human tutor, it must reason about the domain and the learner. This has prompted research in the field of intelligent tutoring system particularly in adaptive hypermedia learning. On the other hand, in a nonlinear system, the effect depends on the values of other inputs, and the relationship is a higher-order function. Neural Network is an approach that can cater nonlinear problems, and an implementation of an algorithm inspired by research into the brain. It is a technology in which computer learns directly from data, thereby assisting in classification, function estimation, data comprehension, and similar tasks. In this paper, we present a neural network model in classifying students level of knowledge acquisition are normalized in the close interval of (0,1), and the performance of neural network model towards these data are compared to the original data.

Design and implementation of an adaptive web-based hypermedia learning system: A prototype

Abstract: Nowadays, internet has become a significant medium for communication in every aspect of human's life including education. Academically, the impact is great that we are moving from real class room to virtual one. World Wide Web environment has a great potential to be a teaching and learning aids for all level of educations, ranging from primary schools to high institutions. It gives a good opportunity for the teachers to put all teaching materials to assist students to learn even outside class hours. However, this internet and hypermedia system has some drawbacks that can cause teaching and learning to be less effective due to its static links and non-linear nodes. One solution is to develop a dynamic environment which incorporates the features of hypermedia and intelligent tutoring system that allows user control and at the same time can adapt to user's ability. This paper aims to present the design and development of a prototype f an adaptive web-based learning system, called SPAtH for teaching and learning C programming on web, that will identify the student's performance based on certain criteria gathered by the student model such as his academic background, preferences and state of knowldge acquisition. This will in turn provide the student with suitable learning materials, exercises and questions appropriately. This paper also discusses AI techniques that can be used by the adaptive engine to make it more flexible and adaptive to the student's needs.

The LECOBA learning companion system: expertise, motivation and teaching

Abstract: A Learning Companion System (LCS) is a variation of an Intelligent Tutoring System (ITS) where besides the tutor and the student a third agent is added a Learning Companion (LC) The exact nature of the role of the learning companion is one of the most important issues of these systems This paper describes an LCS for Boolean Algebra (LECOBA) implemented to explore the role of the companion as a student of the human student (Learning by Teaching) To implement such a system, issues such as the motivation of the student to interact with the companion and the LC's knowledge of the domain had to be dealt with LECOBA provides companions with two types of expertise weak and strong, and two types of motivation Motivated and Free The evaluation of the system suggested that subjects who faced the weak learning companion in the motivated condition showed a trend of greatest learning gain, though the differences were not significant