CONTENTS Page ACKNOWLEDGMENT . . . . . . . . . . . . . . . . . . iii LIST OF TABLES . . . . . . . . . . . . . . . . . . vii LIST OF FIGURES . . . . . . . . . . . . . . . . . viii LIST OF ABBREVIATIONS . . . . . . . . . . . . . . ix CHAPTER I. INTRODUCTION . . . . . . . . . . . . . . 1 1.1 CIRCSIM-Tutor . . . . . . . . . . . 1 1.2 Student Modelling . . . . . . . . . . 3 1.3 Hints . . . . . . . . . . . . . . . . 3 1.4 Organization of Thesis . . . . . . . 5 II. ITS LITERATURE . . . . . . . . . . . . . 6 2.1 Early Attempts at Student Modelling . 6 2.2 Bug and Overlay Paradigms . . . . . . 9 2.3 Other Paradigms . . . . . . . . . . . 11 2.4 Diagnosis . . . . . . . . . . . . . . 12 2.5 Hints . . . . . . . . . . . . . . . . 14 III. THE CST PROJECT . . . . . . . . . . . . . 20 3.1 Methodology . . . . . . . . . . . . . 22 3.2 The CST Domain . . . . . . . . . . . 23 3.3 Keyboard to Keyboard Tutoring Experiments . . . . . . . . . . . . 26 3.4 CST . . . . . . . . . . . . . . . . 30 3.4.1 The Domain

this document as a vector in factor space, starting from the origin. It may be a fairly long vector (because of many words added together) or a short one, but its direction will be determined solely by the relative contributions of the four components. When using Latent Semantic Analysis for information retrieval the collection of documents is analyzed in this manner, producing factor-space vectors for each word and for each document. When a query is processed the query itself is treated as a document: the components of each word are looked up and combined to form a vector for the querydocument. Then the vector representation of the query-document is compared to the vectors for all the stored documents in order to retrieve ones which are similar. A common measure of similarity is the cosine of the angle between the vectors representing two documents. If your query contains only a few words, its vector may be quite short. Yet there should be a way to measure its similarity to documents, which (because they are wordier) may have longer vectors. If the factors in the query and a stored document are in the same proportion (e.g., equal parts education and law 77 enforcement), that document is likely to be one you want to retrieve. In this case the vectors point in the same direction, and the angle between the query vector and stored document vector is very small. LSA in More Detail The particular mathematical model used by Latent Semantic Analysis is called singular value decomposition. The thing being modeled is a matrix of word frequencies in documents: each row of the matrix represents a different word and each column of the matrix represents a different document. A cell of the matrix contains the count of the number of times one word occurs in one document. In general...

Abstract not found

Abstract not found

CONTENTS Page ACKNOWLEDGMENT ........................................................................................................ iii LIST OF TABLES ..................................................................................................................vi LIST OF FIGURES................................................................................................................ vii CHAPTER I. INTRODUCTION ............................................................................................... 1 1.1 Problem Statement................................................................................... 1 1.2 Research Goals......................................................................................... 3 1.3 Organization of This Thesis .................................................................... 4 II. BACKGROUND.................................................................................................. 5 2.1 What is CIRCSIM-TUTOR?............

............................................................................................................ x CHAPTER I. INTRODUCTION .................................................................................. 1 1.1 Problem Statement .................................................................... 1 1.2 Goals ......................................................................................... 4 1.3 Organization of the Thesis ........................................................ 5 II. CIRCSIM-TUTOR ................................................................................. 6 2.1 Domain ...................................................................................... 6 2.2 Structure .................................................................................... 8 2.3 Related Work on CIRCSIM-Tutor ............................................ 12 III. PLANNING ISSUES ............................................................................. 2...

. Research has shown that tutoring by humans provide the most effective method of instruction. One school of thought in the Intelligent Tutoring Systems (ITS) community believes that studying human tutors is the best way to discover how to build effective machine tutors. This paper describes a conceptual model of tutoring that is based on a study of skilled human tutors in the domain of cardiovascular physiology. This model is developed as a part of research to develop an ITS, CIRCSIM-Tutor, for first year medical students at Rush Medical College, Chicago. The major theme of this model of tutoring is that, in a problem-solving environment, it facilitates the student to integrate his/her knowledge into a coherent qualitative causal model of the domain and solve problems in the domain. The key feature of this model is that it uses multiple models of the domain in the process of facilitating knowledge integration. 1 Introduction Tutoring by humans is the most effective method of instruct...

Despite their many successes, Intelligent Tutoring Systems (ITS) are not yet practical enough to be employed in the real world educational/training environments. We argue that this undesirable scenario can be changed by focusing on developing an ITS development methodology that transforms current ITS research to consider practical issues that are part of the main causes of underemployment of ITSs. Here we describe an ambitious research project to develop an ITS that has recently completed its first phase of development at the Computer Research Institute of Montreal. This project aims to address issues, such as, making ITS handle multiple domains, developing cost-effective knowledge assessment methodologies, organizing and structuring domains around curriculum views and addressing the needs of users by considering their immediate goals and educational/training settings. This paper concentrates on the outcomes of the first phase of our project that includes the architecture and functionality (specially user knowledge assessment and pedagogical guidance) of the Intelligent Guide.