Showing papers on "Intelligent tutoring system published in 1998"

Procedural help in Andes: generating hints using a Bayesian network student model

Abstract: One of the most important problems for an intelligent tutoring system is deciding how to respond when a student asks for help. Responding cooperatively requires an understanding of both what solution path the student is pursuing, and the student's current level of domain knowledge. Andes, an intelligent tutoring system for Newtonian physics, refers to a probabilistic student model to make decisions about responding to help requests. Andes' student model uses a Bayesian network that computes a probabilistic assessment of three kinds of information: (I) the student's general knowledge about physics, (2) the student's specific knowledge about the current problem, and (3) the abstract plans that the student may be pursuing to solve the problem. Using this model, Andes provides feedback and hints tailored to the student's knowledge and goals.

The Foundations and Architecture of Autotutor

Abstract: The Tutoring Research Group at the University of Memphis is developing an intelligent tutoring system which takes advantages of recent technological advances in the areas of semantic processing of natural language, world knowledge representation, multimedia interfaces, and fuzzy descriptions. The tutoring interaction is based on in-depth studies of human tutors, both skilled and unskilled. Latent semantic analysis will be used to semantically process and provide a representation for the student's contributions. Fuzzy production rules select appropriate topics and tutor dialogue moves from a rich curriculum script. The production rules will implement a variety of different tutoring styles, from a basic untrained tutor to one which uses sophisticated pedagogical strategies. The tutor will be evaluated on the naturalness of its interaction, with Turing-style tests, by comparing different tutoring styles, and by judging learning outcomes.

Component-Based Construction of a Science Learning Space

Abstract: We present a vision for learning environments, called Science Learning Spaces, that are rich in engaging content and activities, provide constructive experiences in scientific process skills, and are as instructionally effective as a personal tutor. A Science Learning Space combines three independent software systems: 1) lab/field simulations in which experiments are run and data is collected, 2) modeling/construction tools in which data representations are created, analyzed and presented, and 3) tutor agents that provide just-in-time assistance in higher order skills like experimental strategy, representational tool choice, conjecturing, and argument. We believe that achieving this ambitious vision will require collaborative efforts facilitated by a component-based software architecture. We have created a feasibility demonstration that serves as an example and a call for further work toward achieving this vision. In our demonstration, we combined 1) the Active Illustrations lab simulation environment, 2) the Belvedere argumentation environment, and 3) a modeltracing Experimentation Tutor Agent. We illustrate student interaction in this Learning Space and discuss the requirements, advantages, and challenges in creating one.

Using a Learning Agent with a Student Model

Abstract: In this paper we describe the application of machine learning to the problem of constructing a student model for an intelligent tutoring system. The proposed system learns on a per student basis how long an individual student requires to solve the problem presented by the tutor. This model of relative problem difficulty is learned within a "two-phase" learning algorithm. First, data from the entire student population are used to train a neural network. Second, the system learns how to modify the neural network's output to better fit each individual student's performance. Both components of the model proved useful in improving its accuracy. This model of time to solve a problem is used by the tutor to control the complexity of problems presented to the student.

GTE: An Epistemological Approach to Instructional Modelling.

Abstract: The instructional competence of an Intelligent Tutoring System lies in its instructional model. Such a model has been approached in the ITS field from a theoretical and from a computational point of view. GTE approaches the instructional model from an epistemological point of view by making it reflect the instructional knowledge and expertise that underlies human teaching. The underlying assumption is that such knowledge and expertise has a generic nature, and that it can be modelled. The central component of the GTE architecture is therefore a large generic instructional knowledge base that is capable of dynamically generating a huge variety of instructional plans. It enables to flexibly adapt the teaching performance to the requirements of the individual teaching context. In this paper we describe the formalism that was developed for the representation of the instructional knowledge, the interpretation engine that can generate instructional processes based on the knowledge in the knowledge base, and the actual content of the knowledge base. It illustrates the feasibility of the assumption that was made, and the impact this may have on authoring instructional strategies.

Authoring Content in the PAT Algebra Tutor

Abstract: Most authoring tools for intelligent tutoring systems are targeted towards a broad range of applications. Such systems have expressive power but gain the complexity inherent in any general programming language. This paper considers a different kind of authoring tool, focused on creating content for a specific intelligent tutoring system. The resulting system, called pSAT, addresses the great demand for continuing development of content. A system like pSAT needs to be easily learned by end-users and needs to provide feedback adequate for the user to be able to determine that the system will correctly present the content under a wide range of user strategies, preferences and abilities. We focus on design principles driven by these considerations and conclude with a development strategy that begins with a closely-focused content authoring system and then broadens to a system that can more fundamentally affect the type of content presented by the intelligent tutoring system. Reviewers: Chris DiGiano (SRI), Greg Kearsley (Nova Southeastern U.), Henry Lieberman (MIT) Interactive elements: The Problem Situation Authoring Tool (pSAT) described in this article is available online. Demonstration: The Problem Situation Authoring Tool (pSAT) described in this article is available at http://domino.psy.cmu.edu:81/best/psat.html . An online version of the Practical Algebra Tutor, PAT OnLine, is available at http://domino.psy.cmu.edu/patonline.html .

Cognotive Task Analysis in Service of Intelligent Tutoring System Design: A Case Study in Statistics

Abstract: Cognitive task analysis involves identifying the components of a task that are required for adequate performance. It is thus an important step in ITS design because it circumscribes the curriculum to be taught and provides a decomposition of that curriculum into the knowledge and subskills students must learn. This paper describes several different kinds of cognitive task analysis and organizes them according to a taxonomy of theoretical/empirical ∞ prescriptive/descriptive approaches. Examples are drawn from the analysis of a particular statistical reasoning task. The discussion centers on how different approaches to task analysis provide different perspectives on the decomposition of a complex skill and compares these approaches to more traditional methods.

Authoring Tools for Component-Based Learning Environments

Abstract: We argue that a focus on building an authoring tool for a complete learning environment is misplaced. An analysis of the task of authoring a commercial educational system reveals it to be best accomplished through authoring separate components. For some of these components, authoring tools already exist and need not be duplicated for use in educational systems. Connecting the various components together is a separate authoring task, and parts of this task are different for educational systems than for typical component-based software. The last part of this paper describes the current way in which our model—tracing ITSs are constructed .

A comprehensive method for the evaluation of complete intelligent tutoring systems

Abstract: Although it is generally believed that intelligent tutoring systems promise a great potential for education, little work has been done on the development of an appropriate evaluation method to assess these systems. This paper proposes an evaluation approach that serves to deliver comprehensive suggestions for the overall improvement of both the architecture and the behaviour of a complete intelligent tutoring system.

Providing Feedback to Equation Entries in an Intelligent Tutoring System for Physics

Abstract: Andes, an intelligent tutoring system for Newtonian physics, provides an environment for students to solve quantitative physics problems. Andes provides immediate correct/incorrect feedback to each student entry during problem solving. When a student enters an equation, Andes must (1) determine quickly whether that equation is correct, and (2) provide helpful feedback indicating what is wrong with the student's entry. To address the former, we match student equations against a pregenerated list of correct equations. To address the latter, we use the pre-generated equations to infer what equation the student may have been trying to enter, and generate hints based on the discrepancies. This paper describes the representation of equations and the procedures Andes uses to perform these tasks.

Cognitive Tools for Assessment and Learning in a High Information Flow Environment

Abstract: A simulation-based intelligent tutoring system (ITS) was designed for nurses working in a Surgical Intensive Care Unit (SICU). A cognitive task analysis approach was used to identify the cognitive components of clinical decision making of “expert” surgical nurses. Quantitative analyses revealed that expert nurses reached the same decisions. However, a qualitative analysis of the verbal protocols revealed great variability in how the nurses arrived at their clinical decisions. Differences were observed in: hypothesis generation, planning of medical interventions, actions performed, results of evidence gathering, interpretation of the results, heuristics, and the overall solution paths. The results of these analyses were used to design a prototype ITS. The tutoring environment (SICUN) is described in terms of the cognitive tools it provides, and the assessment opportunities it presents. Implications for the evaluation of this system are discussed.

A new approach to ITS-curriculum and course authoring: the authoring environment

Abstract: The aim of this paper is to present an authoring environment dedicated to the development of curriculum and course material that can be handled by an Intelligent Tutoring System (ITS). The adopted curriculum model is CREAM (Curriculum Representation and Acquisition Model) which represents subject-matter content from the domain, the pedagogical and the didactic points of view. The authoring environment, called CREAM-Tools, consists of a set of tools able to create and edit all of the elements (domain knowledge, instructional objective, didactic resources, pedagogical and didactic model) of a curriculum. This set of tools contains, among others, graphical editors, intelligent assistance and knowledge browsers. The environment also includes a course generation kit that allows a designer to generate a course by specifying a target public and a course description. This paper also presents curriculum and course development approaches (methodologies). The delivery of curriculums and courses produced from this environment is done by an object-oriented ITS. The teaching process is supported by new technologies such as World-Wide Web browsers. We also show ways in which other modules in an intelligent tutoring system can exploit the resulting curriculums and courses in the teaching-learning process.

Creating More Versatile Intelligent Learning Environments with a Component-Based Architecture

Abstract: In this paper we show that, with an appropriate component-based architecture, new functionality can be added to an Intelligent Tutoring System (ITS) with minimal effort. In particular, we show that an explanation function can be added to a component-based ITS which was originally designed to support activity in a learning-by-doing environment. We support these two claims by presenting our recent efforts to extend the Java Algebra Tutor, a variant of the PAT algebra tutor, with a generic example explanation module.

Facilitating the Development and Use of Interactive Learning Environments

Abstract: Part 1 Tools of the Trade: Developing Learning Technology in Practice, W.J. Clancey Using Quasi-Experimentation to Gather Design Information for Intelligent Tutoring Systems, A.S. Wolff et al Cost Benefits Analysis for Computer-Based Tutoring Systems, A.S. Wolff. Part 2 Case Studies from Industry: Introducing Advanced Technology Applications Into Corporate Environments, C.P. Bloom et al An Observational Study of ITS Knowledge Base Development by Non-Technical Subject Matter Experts, A. McClard Supporting Developmnt of On-Line Task Guidance for Software System Users - Lessons from the WITS Project, R. Farrell and L.S. Lefkowitz Transferring Learning Systems Technology to Corporate Training Organizations - An Examination of Acceptance Issues, P.T. Bullemer and C.P. Bloom Augmenting Intelligent Tutoring Systems with Intelligent Tutors, R. Radlinksi and M.E. Atwood. Part 3 Case Studies from Government: "...A Prophet Without Honour..." Case Histories of ITS Technology at NASA/Johnson Space Centre, R.B. Loftin Sherlock II - an Intelligent Tutoring System Built Upon LRDC Tutor Framework, S. Katz et al Are Intelligent Tutoring Systems Ready for the Commercial Market?, J.E. Norton et al.

TAP: a software architecture for an inquiry dialogue-based tutoring system

Abstract: In the tutoring agenda planner (TAP) project, we study the feasibility of implementing the inquiry teaching method of Collins and Stevens (1991) as tutoring software. This paper describes the software architecture for TAP-1-a simple inquiry tutoring shell based on the theory of inquiry teaching. The inquiry teaching style has the objective of teaching scientific reasoning skills through a "localized" sequence of well-planned inquiry dialogue. To complement the "localized" dialogue planning framework inherent in the theory of inquiry teaching, the TAP-1 architecture has adopted the "global" curriculum planning technique. TAP-1 has successfully demonstrated the inquiry teaching style through an inquiry planner within an intelligent tutoring system shell. In addition, PADI-a geography tutor that delivers inquiry teaching style-has been implemented using TAP-1. A group of students performed well in an evaluation activity of the tutor. They also foresaw the potential of TAP for achieving the aim of cultivating scientific thoughts.

Towards an Intelligent Tutoring System Architecturethat Supports Remedial Tutoring

Abstract: For successful teaching to take place an intelligent tutoring system has to be able to cope with any student errors that may occur during a tutoring interaction. Remedial tutoring is increasingly viewed as a central part of the overall tutoring process, and recent research calls for adaptive remedial tutoring. This paper discusses the issues of remedial tutoring that have been proposed or implemented to support efficient remedial tutoring. These issues serve to uncover any underlying principles of remediation that govern remedial tutoring with intelligent tutoring systems. In order to incorporate these principles of remediation into intelligent tutoring systems development processes this paper continues with the development of a model that can be employed in the development of an intelligent tutoring system that is capable of offering remedial tutoring according to these principles. This model is a formalisation of remedial interventions with intelligent tutoring systems. To demonstrate how the model can be employed in developing an intelligent tutoring system, INTUITION, the implementation of an existing business simulation game, has been developed. This paper concludes with an illustration of how the model for remedial operations provides for remedial tutoring within INTUITION. The evaluation of INTUITION shows that the model for remedial operations is a useful method for providing efficient remedial tutoring.

A Framework for Developing Intelligent Tutoring Systems Incorporating Reusability

Abstract: The need for effective tutoring and training is mounting, especially in industry and engineering fields, which demand the learning of complex tasks and knowledge. Intelligent tutoring systems are being employed for this purpose, thus creating a need for cost-effective means of developing tutoring systems. We discuss a novel approach to developing an Intelligent Tutoring System shell that can generate tutoring systems for a wide range of domains. Our focus is to develop an ITS shell framework for the class of Generic Task expert systems. We describe the development of an ITS for an existing expert system, which serves as an evaluation test-bed for our approach.

Responding to Unexpected Student Utterances in CIRCSIM-Tutor v.3: Analysis of Transcripts

Abstract: CIRCSIM-Tutor is a dialogue-based intelligent tutoring system that conducts dialogues with medical students about blood pressure regulation. To obtain models for computergenerated dialogues, we analyzed dialogues involving expert human tutors. In this paper we describe some of the interesting and complex patterns we isolated from the human tutorial dialogues in cases where the student gave erroneous or otherwise unexpected results.

An Advanced Embedded Training Systems (AETS) for Tactical Team Training

Abstract: The Advanced Embedded Training System (AETS) applies intelligent tutoring systems technology to improve tactical training quality and reduce manpower needs in simulation-based shipboard team training. AETS provides layers of performance assessment, cognitive diagnosis, and instructorsupport on top of the existing embedded mission simulation capability. Detailed cognitive models of trainee task performance are used to drive the assessment, diagnosis and instructional functions of the system.

Rediscovering Learning: Acquiring Expertise in Real World Problem Solving Tasks

Abstract: : The importance of continuous learning in high-tech work settings is being rediscovered as industry and the military services react to external forces such as increasingly complex and rapidly changing equipment systems as well as highly competitive product service markets. Competitiveness in turn dictates a leaner, downsized workforce for the private sector, and diminished defense spending has resulted in dramatic losses of personnel in the Armed Forces. Those who remain are expected to do more, and yet, performance demands routinely override training opportunities. Moreover on the job training that follows either the traditional master apprentice behavioral model or relies heavily on didactic instruction is typically impractical or ineffective. An alternative learning oriented approach that accelerates skill acquisition in high-tech jobs is described here. With this approach cognitive performance models provide both the input to instruction and the desired criterion performance to be attained. The instructional medium is an intelligent tutoring system. A knowledge elicitation approach called the PARI cognitive task analysis methodology is described, along with the cognitive models of performance yielded by this analysis. The performance models in turn inform a coached apprenticeship practice environment embodied in an intelligent computer tutor. The system was recently evaluated in a controlled experiment at three geographically separated Air Force workcenters. Results reveal that the experimental group significantly accelerated their acquisition of problem solving skills when compared to a matched control group; moreover, their newly acquired troubleshooting skills generalized to a novel equipment system.

Work in Progress: A Visual Specification of Knowledge Bases

Abstract: The paper presents the research framework for the design of a special software environment to support visual knowledge base design and specification. Flexible user centred graphical interface is described. The approach is aimed at three interrelated topics: knowledge specification, visual structuring and hypertext design. The proposed ideas and methods may be applied to those systems where structured analysis of data and knowledge is of special interest, such as intelligent tutoring systems, expert systems, decision support, etc.

DNA - Uncorking the Bottleneck in Knowledge Elicitation and Organization

Abstract: There are two main purposes of this paper. First, we describe a novel cognitive tool that was designed to aid in knowledge elicitation and organization for instructional purposes - specifically to be used for intelligent tutoring system development. This automated approach to knowledge elicitation is embodied in a program called DNA (Decompose, Network, Assess). Our aim for this tool is to increase the efficiency of developing the expert model - often referred to as the bottleneck in developing intelligent instructional systems. The second purpose is to present a first-order summative evaluation of the tool's efficacy. Specifically, we used DNA with three statistical experts to explicate their knowledge structures related to measures of central tendency. In short, we found that DNA can be used as a standalone program to effectively elicit relevant information on which to build instruction. This was achieved in hours compared to months for conventional elicitation procedures.

Multi-Agent Architecture for Intelligent Tutoring Systems

Abstract: This paper shows a multi-agent architecture based on reactive agents for an intelligent tutoring system (ITS). The global system behavior is modeled taking into account the mental models and the cognitive task analysis. We present the basic characteristics of the reactive system in terms of reactive robotics, where they started. Next we introduce some definitions and schemes in order to characterize the multi-agent architecture. Finally, we present an ITS example called Makatsina Makatsina means tutor in TOTONACA, a Mexican pre-Spanish language. which teaches the skills necessary to solve a truss analysis problem by the joint method. This domain is an integration skill.

Successful pedagogical applications of symbolic computation

Abstract: At the Education Program for Gifted Youth (EPGY) we have developed a series of stand-alone, multi-media computer-based courses designed to teach advanced students mathematics at the secondary-school and college level. The EPGY course software has been designed to be used in those settings where a regular class cannot be offered, either because of an insufficient number of students to take the course or the absence of a qualified instructor to teach the course. In this way it differs from traditional applications of computers in education, most of which are intended to be used primarily as supplements and in conjunction with a human teacher.

Relationship between tutorial goals and sentence structure in a corpus of tutoring transcripts

Abstract: An intelligent tutoring system, CIRCSIM- Tutor tutors first-year medical students on blood pressure regulation based on the dialogue patterns of human tutors. To obtain data about the language and conversation patterns of human tutors, we analyzed transcripts of human tutors working over a modem, then annotated them to show tutorial goal structure. In this paper we analyze clusters of sentences serving the same tutorial goal. We attempt to determine the information content required by each group and possible sources of these content elements. We show potential surface structures which could be generated from these elements. We discuss the influence on our work of the theories of Michael Halliday and Deborah Schiffrin. The results of this work will assist us in building a text generation system for CIRCSIM-Tutor v. 3 which will mimic some of the natural qualities of the speech of human tutors in a simple and efficient manner.

Towards an Intelligent Tutoring System for Situation Awareness Training in Complex, Dynamic Environments

Abstract: Some accidents in complex systems have been attributed to a lack of situation awareness. Despite increased use of automation and improvements in display design, accidents of these types have not been eliminated. One option is to train operators to acquire and to maintain situation awareness. This paper describes an instructional design, human-computer interface, and the computational architecture for implementing an intelligent tutoring system for training situation awareness. The system furnishes detailed guidance in the early practice stages of training and provides performance feedback in the reinforcement stages of training. The system includes a debriefing capability to structure the review after performance and aid in the evaluation of student performance.

An Intelligent Tutoring System for Teaching Formal Languages

Abstract: The paper describes design of the FLUTE system, an intelligent tutoring system in the domain of formal languages and automata. The basic idea of the FLUTE system is a systematic introduction of students into the system's domain, in accordance with both the logical structure of the domain and individual background knowledge and learning capabilities of each student. Other intelligent tutoring systems in that domain are not described in the open literature. The knowledge in the FLUTE system is represented using a recently developed object-oriented model of intelligent tutoring systems, called GETBITS. A brief overview of the model is also included. The contents that should be presented to the student during tutoring sessions are discussed and logical organization of such contents within the system is described. The system implementation is based on a number of design patterns and class libraries developed in order to support building of intelligent systems. The system is analyzed in the paper from the pedagogical point of view. Every concept that a student has to learn during a session with FLUTE, the system illustrates by a number of examples. This makes the tutoring process more dynamic and facilitates learning.

SARA: A Case-Based Student Modelling System

Abstract: This paper describes an Intelligent Tutoring System (ITS) called SARA. This system is developed using a new student modelling technique based on Case-Based Reasoning (CBR). SARA is organized around two main knowledge bases, the problems base and the cases base. The architecture of the system consists of several components. The functionality of each component and its relationships with the other components will be shown. Two ways of using the system will be presented: (1) as a system for student modelling, and (2) as a server providing information to be used by people testing or by applications using these services. We will also study the process of building the student model with this system. The student model constructed by SARA represents two important aspects of a student, namely the knowledge component and the inferences model.

Student Initiatives and Tutor Responses in a Medical Tutoring System

Abstract: This paper attempts to classify student initiatives and tutor responses in transcripts of human tutoring sessions by looking at the interaction between them. We define a student initiative as any attempt by the student to seize control for changing the course of the dialogue. Student initiatives are classified in four dimensions: the surface form, the communicative goal, the content area, and the degree of certainty expressed. (Does the student hedge or not?) The tutor responses are classified in three dimensions: the surface form, the delivery mode, and the communicative goal. We undertook this research in order to discover how our intelligent tutoring system could respond more intelligently to the student. We are convinced that the recognition of initiatives depends on identification of student plans. This represents a first step in our system toward mixed-initiative dialogue.