Development Of Intelligent Tutoring Systems Research Articles

Multi-Agent and Service Oriented Architectures for Intelligent Tutoring System Development

Multi-Agent and Service Oriented Architectures for Intelligent Tutoring System DevelopmentTraditional modular architecture of Intelligent Tutoring Systems (ITSs) does not provide sufficient modularity of complex ITSs. Distributed technologies like services and agents are used to increase modularity of ITSs by implementing traditional modules as sets of services or agents. The paper describes holonic agent architecture that implements each module as one or more holonic agents. It uses the lessons learned from the multi-agent architecture to propose service oriented ITS architecture.

Agent based affective tutoring systems: A pilot study

An important trend in the development of Intelligent tutoring systems (ITSs) has been that providing the student with a more personalized and friendly environment for learning. Many researchers now feel strongly that the ITSs would significantly improve performance if they could adapt to the affective state of the learner. This idea has spawned the developing field of affective tutoring systems (ATSs): ATSs are ITSs that are able to adapt to the affective state of students. However, ATSs are not widely employed in the tutoring system market. In this paper, a survey was conducted to investigate the critical factors affecting learner’s satisfaction in ATSs based on an ATS developed by us. The results revealed that learner’s attitude toward affective computing, agent tutor’s expressiveness, emotion recognition accuracy, number of emotions recognized by agent tutor, pedagogical action and easy of the use of the system have significant influence on learner’s satisfaction. The results indicate institutions how to further strengthen the ATSs’ implementation.

Multi-Agent Based Intelligent Tutoring System Source Code Generation Using MASITS Tool

Multi-Agent Based Intelligent Tutoring System Source Code Generation Using MASITS ToolSeveral agent development tools have been proposed. At the same time, specific tools for agent based Intelligent Tutoring System (ITS) development do not exist. However, ITSs have some specific characteristics that must be taken into consideration during the development. General purpose Agent Oriented Software Engineering (AOSE) methodologies and therefore development tools do not sufficiently correspond to the characteristics of ITSs. Additionally, the general purpose AOSE methodologies and tools do not allow plugging in domain specific rules and diagrams. Thus, usage of knowledge gained in ITS research during the development process is limited. In the absence of general tools that allow plugging in knowledge from ITS research, a specific tool named MASITS has been developed. The tool supports a specific agent based ITS development methodology named MASITS which takes into consideration specific characteristics of ITSs and integrates knowledge from ITS research. The tool supports all phases of ITS development, starting from requirements analysis and ending with deployment. Requirements analysis and design phases are supported by appropriate diagram creation tools. Implementation is supported by source code generation from diagrams created during the design phase. JADE platform is used for agent implementation. Thus, Java classes for ontology, agents and behaviours are generated from the design diagrams. The paper includes a brief overview of diagrams used in the source code generation and detailed algorithms for source code generation from the diagrams.

ITS-LAGUNTXO: enhancing the integration of people with intellectual disabilities

In order to face the problems that people with disabilities find in their integration into social and working environments, one of the key issues is the implementation of solutions offered by new technologies by using what experts call 'support technologies'. The development of intelligent tutoring systems (ITS) based on mobile platforms offers new perspectives for better integration of people with disabilities. The LAGUNTXO System aims to achieve the performance of human tutors, going a step beyond classical tutoring systems that perform just organisational tasks. Due to the wide diversity of people with disabilities, an intelligent structure that may achieve a convenient tutoring system configuration for each case has been incorporated. With an appropriate design of the structure and architecture of this task handler, it is very easy to operate by stakeholders. An automaton-based mechanism has been performed to technologically adapt the large amount of possibilities related to the interaction between people with disabilities, the task that is going to be made autonomously by users and the mobile system elements. In this paper, LAGUNTXO architecture, operational ways and a pilot study are presented.

Scaling Up Programming by Demonstration for Intelligent Tutoring Systems Development: An Open-Access Web Site for Middle School Mathematics Learning

Intelligent tutoring systems (ITSs), which provide step-by-step guidance to students in complex problem-solving activities, have been shown to enhance student learning in a range of domains. However, they tend to be difficult to build. Our project investigates whether the process of authoring an ITS can be simplified, while at the same time maintaining the characteristics that make ITS effective, and also maintaining the ability to support large-scale tutor development. Specifically, our project tests whether authoring tools based on programming-by-demonstration techniques (developed in prior research) can support the development of a large-scale, real-world tutor. We are creating an open-access Web site, called Mathtutor (http://webmathtutor.org), where middle school students can solve math problems with step-by-step guidance from ITS. The Mathtutor site fields example-tracing tutors, a novel type of ITS that are built "by demonstration," without programming, using the cognitive tutor authoring tools (CTATs). The project's main contribution will be that it represents a stringent test of large-scale tutor authoring through programming by demonstration. A secondary contribution will be that it tests whether an open-access site (i.e., a site that is widely and freely available) with software tutors for math learning can attract and sustain user interest and learning on a large scale.

Requirements analysis of Multi-Agent Based Intelligent Tutoring Systems

Requirements analysis of Multi-Agent Based Intelligent Tutoring SystemsThe agent oriented software engineering research proposes general assumptions for agent oriented software development, while intelligent tutoring system (ITS) research proposes specific ITS architecture and other specific knowledge for ITS development. Both of these views should be taken into consideration while developing multi-agent based ITSs. Thus there is a need for specific approaches for all phases of agent based ITS development which take into consideration main ideas from both agent oriented software engineering and ITS research. In this paper we propose a requirements analysis approach for multi-agent based ITSs. A case study of a simple ITS is included, too. Requirements analysis in the proposed approach consist of two main steps, namely goal modelling and use case modelling. During the goal modelling the main goals of the system are identified and a goal hierarchy for the system is created. During the use case modelling use cases needed to achieve each lower level goal and their descriptions are created. The proposed approach of the requirements analysis is intended to be a part of the full life cycle methodology for multi-agent based ITS development. The developed use case model (especially use case scenarios) is used during the agent interaction design and task definition. Goal hierarchy during the design phase is mainly used for checking, if the results of design achieve all system's goals.

Design of Multi-Agent Based Intelligent Tutoring Systems

Design of Multi-Agent Based Intelligent Tutoring SystemsResearch of two fields, namely agent oriented software engineering and intelligent tutoring systems, have to be taken into consideration, during the design of multi-agent based intelligent tutoring systems (ITS). Thus there is a need for specific approaches for agent based ITS design, which take into consideration main ideas from both fields. In this paper we propose a top down design approach for multi-agent based ITSs. The proposed design approach consists of the two main stages: external design and internal design of agents. During the external design phase the behaviour of agents and interactions among them are designed. The following steps are done: task modelling and task allocation to agents, use case map creation, agent interaction design, ontology creation and holon design. During the external design phase agents and holons are defined according to the holonic multi-agent architecture for ITS development. During the internal design stage the internal structure of agents is specified. The internal structure of each agent is represented in the specific diagram, called internal view of the agent, consisting of agent's actions and interactions among them, rules for incoming message and perception processing, incoming and outgoing messages, and beliefs of the agent. The proposed approach is intended to be a part of the full life cycle methodology for multi-agent based ITS development. The approach is developed using the same concepts as JADE agent platform and is suitable for agent code generation from the design diagrams.

Reusing task-specific knowledge-based systems to generate intelligent tutoring systems

This work advances the knowledge-based systems paradigm to address the need for reusable Intelligent Tutoring Systems (ITSs), and more cost-effective ITS development methods. We describe a novel approach and architecture that can interact with task-specific knowledge-based systems to automatically generate ITSs for the domains represented by those systems. Our approach facilitates the reuse of both intelligent tutoring components, and problem solving and domain knowledge embedded within knowledge-based systems for tutoring. We describe the development of the architecture, report two case studies on using the architecture to generate ITSs for two very different domains, and present and evaluate our results.

Like pedagogical design, educational system design can benefit from a framework-oriented approach

Instructional designers and teachers, at all levels of education and training, try to put in common, to share and to reuse the practices affecting their pedagogical design and expertise. However, the instructional environment, and in particular the design and development of educational systems, can benefit from similar knowledge sharing, especially because of the difficulty, length and cost of this development process. In this paper, we aim to show how building educational systems can be more effective and beneficial using a framework-oriented approach. To do so, we describe different levels of abstraction in the design and the development of an Intelligent Tutoring System (ITS). We first recall what an ITS is, showing its advantages and drawbacks, and identifying different knowledge types. To tackle the limitations of the ITS construction, we then propose to build a framework, including guidelines and tools to ease its development. We finally show that a collaborative framework-oriented approach is indeed feasible, describing how to build such a framework. We thus try to promote reusability and extensibility in many aspects of the design and development of ITSs.

Using psychometric technology in educational assessment: The case of a schema-based isomorphic approach to the automatic generation of quantitative reasoning items

This article deals with the investigation of the psychometric quality and constructs validity of algebra word problems generated by means of a schema-based version of the automatic min–max approach. Based on review of the research literature in algebra word problem solving and automatic item generation this new approach is introduced as a theory-based top–down method of automatic item generation featuring a quality control framework aimed to minimize the construct unrelated variance in the item parameters. The first study deals with the evaluation of an initial set of items. The results are replicated in the second study using a larger item set which also allows the investigation of the construct representation of the generated item. Since construct unrelated variance components (e.g. reading comprehension) have been controlled for in the item generation phase the results revealed some interesting insights into the cognitive processes of the actual mathematization phase of algebra word problem solving. The third study investigated the nomothetic span is using hierarchical confirmatory factor analysis. The results argue for the convergent and discriminant validity of the automatically generated items. Taken together, the results indicate that the automatic generation of construct valid algebra word problems at a high psychometric level is viable. The discussion is thus concerned with the implications of this new approach to item generation for theory development and evaluation as well as practical benefits for educational assessment and the development of intelligent tutoring systems.

EpiList: An Intelligent Tutoring System Shell for Implicit Development of Generic Cognitive Skills That Support Bottom-Up Knowledge Construction

Current research efforts have shifted from the development of intelligent tutoring systems (ITSs) that focus on the teaching of "content" knowledge to those that focus on teaching cognitive skills. This shift is seen as necessary because cognitive skills are increasingly recognized by educational establishments as the foundation for knowledge acquisition, comprehension, and application. Knowledge construction is a cognitive skill and can be broadly divided into "top-down" and "bottom-up" approaches. The former splits a concept to form subordinate concepts, while the latter one groups concepts together to form a superordinate concept. Both approaches require the skill of classification and form different semantic networks or classification schemes with different levels of significance and suitability. List-making games operate within a bottom-up environment, where one has to arrange a list of items according to their respective categories. EpiList is developed along the line of a list-making game. It requires the student to suitably arrange items into categories that they have selected from a given list of categories. EpiList has employed both inductive and deductive teaching strategies to tutor the students and implicitly teach them the skills of generalization and comparison. This is achieved through the use of rules and algorithms. The rules and algorithms focus not only on the incorrect categorization of items but also on the migration of one classification scheme to another scheme that is more significant and suitable under the current teaching context. This paper computationally translates the teaching of cognitive skills into simple sets and represents the instructional process in terms of rules and algorithms operating on these sets. The field evaluations of EpiList demonstrated its capability to develop generic cognitive skills

지능형 교육 시스템을 위한 적응적 지식베이스 객체 모형 개발

Intelligent Tutoring System(ITS), which offers individualized learning environment that consider many learners` variable, is realized by the effective alternative to take the place of domain expert. Accordingly, research on Learning Companion System(LC) is currently noticing. However, to develop LCS which applies effective interaction, it is necessary to combine several LCs, and personalized knowledge base have to be made first. Therefore, in this paper, we propose the `Knowledge Base Object Medel`, which is based on connectionist` in cognition structure, represents learner`s knowledge to self-learnig object, and grows adaptive object by proprietor, verify the validity. This model lays the groundwork for design of personalized knowledge base, offers clue to development of adaptive ITS using knowledge base object.

Implementing tutoring strategies into a patient simulator for clinical reasoning learning

This paper describes an approach for developing intelligent tutoring systems (ITS) for teaching clinical reasoning. Our approach to ITS for clinical reasoning uses a novel hybrid knowledge representation for the pedagogic model, combining finite state machines to model different phases in the diagnostic process, production rules to model triggering conditions for feedback in different phases, temporal logic to express triggering conditions based upon past states of the student's problem solving trace, and finite state machines to model feedback dialogues between the student and TeachMed. The expert model is represented by an influence diagram capturing the relationship between evidence and hypotheses related to a clinical case. This approach is implemented into TeachMed, a patient simulator we are developing to support clinical reasoning learning for a problem-based learning medical curriculum at our institution; we demonstrate some scenarios of tutoring feedback generated using this approach. Each of the knowledge representation formalisms that we use has already been proven successful in different applications of artificial intelligence and software engineering, but their integration into a coherent pedagogic model as we propose is unique. The examples we discuss illustrate the effectiveness of this approach, making it promising for the development of complex ITS, not only for clinical reasoning learning, but potentially for other domains as well.

Why Do Only Some Events Cause Learning During Human Tutoring?

Developers of intelligent tutoring systems would like to know what human tutors do and which activities are responsible for their success in tutoring. We address these questions by comparing episodes where tutoring does and does not cause learning. Approximately 125 hr of tutorial dialog between expert human tutors and physics students are analyzed to see what features of the dialog are associated with learning. Successful learning appears to require that the student reach an impasse. When students were not at an impasse, learning was uncommon regardless of the tutorial explanations employed. On the other hand, once students were at an impasse, tutorial explanations were sometimes associated with learning. Moreover, for different types of knowledge, different types of tutorial explanations were associated with learning different types of knowledge.

Redefining the learning companion: the past, present, and future of educational agents

The development of intelligent tutoring systems has long been the focus of applying artificial intelligence and cognitive science in education. A new breed of intelligent learning environments called learning companion systems was developed over a decade ago. In contrast to an intelligent tutoring system, in which a computer mimics an intelligent tutor, the learning companion system assumes two roles, one as an intelligent tutor and another as a learning companion. Motivated by recent interest in agent research and other technologies, this learning companion field has received increasing attention. This study addresses issues that arise from different perspectives on this research effort. With a view to future networked learning environments, the learning companion is redefined for application to a wide spectrum of educational agent research. Accordingly, several subjects that relate to educational agents, and hence learning companions, are identified.

Agent-controlled internet tools for computer-based distance training in industry and education

The paper examines ways in which standard internet-based tools and existing packages can be enhanced so as to provide efficient and cost-effective training both in academia and in industry. Aspects such as using existing CAI and CAD packages in conjunction with internet-based tools, the development of intelligent tutoring systems to assist the learning process and the existence of an environment for sharing information and resources are being considered as possible applications for such a development. The recent web presence of packages such as Matlab and Mathematica have also made this development more relevant from an educational viewpoint as both packages are used for training and both require further enhancement in their new role. We see the use of intelligent agents for the enhancement and subsequent control of such tools and packages as essential to the process of distance learning since the latter entails not only efficient communication over the internet, but it also requires the efficient control and management of a) access to facilities and software, b) user direction to the requested relevant information, b) protocols of information exchange between users and relevant software, c) techniques through which multiple distance tutoring can be effected, d) online decision support systems.

Development of intelligent tutoring systems using knowledge structures

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.

CyclePad: An articulate virtual laboratory for engineering thermodynamics

One of the original motivations for research in qualitative physics was the development of intelligent tutoring systems and learning environments for physical domains and complex systems. This article demonstrates how a synergistic combination of qualitative reasoning and other AI techniques can be used to create an intelligent learning environment for students learning to analyze and design thermodynamic cycles. Pedagogically this problem is important because thermodynamic cycles express the key properties of systems which interconvert work and heat, such as power plants, propulsion systems, refrigerators, and heat pumps, and the study of thermodynamic cycles occupies a major portion of an engineering student's training in thermodynamics. This article describes CyclePad, a fully implemented articulate virtual laboratory that captures a substantial fraction of the knowledge in an introductory thermodynamics textbook and provides explanations of calculations and coaching support for students who are learning the principles of such cycles. CyclePad employs a distributed coaching model, where a combination of on-board facilities and a server-based coach accessed via email provide help for students, using a combination of teleological and case-based reasoning. CyclePad is a fielded system, in routine use in classrooms scattered all over the world. We analyze the combination of ideas that made CyclePad possible and comment on some lessons learned about the utility of various AI techniques based on our experience in fielding CyclePad.

The Knowledge Arena as an Extension to the Concept Map: Reflection in Action

The concept map is becoming a ubiquitous tool in education. In recent years there has been a growing interest in “diagramming” or “mapping” ideas to be learned (e.g., Jonassen et al., 1998). The approach has been championed by study skills proponents such as Buzan (1993). Maps of concepts and relationships have been used by many researchers and practitioners to help diagnose misunderstanding, improve study methods and glimpse how learners come to know. In other areas, the representation of knowledge in formalisms such as the Net greatly assisted the development of intelligent tutoring systems (e.g., Sowa, 1983). In order to better understand the claims made for its efficacy, reference to how concept maps have been used and defined will lead to a plausible explanation of the process of “off–loading” of concepts during learning or study (McAleese, 1994, 1998). In order to demonstrate the widespread application of supporting learn ers with external “learning spaces” (c.f. ISLEs/ and REALs—Grabinger et al., 1998; Grabinger & Dunlap, 1995; MacFarlane, 1993), consideration will be given in this paper to techniques that formally represent knowledge in Concept–Relationship–Concept “instances” (Fisher et al., 1990). Other techniques such as reflection journals draw on the same process but are not considered in detail here. The importance of self regulation (Zimmerman, 1990) and self-confrontation (McAleese, 1985) is highlighted in this framework. The map as a mirror or an assistant to learners is well documented (e.g., Vizcarro & Leon, 1998); the question of an external representation of thinking, in the form of a map determining what can be learned as well as what might be learned, is not yet fully known.

Intelligent tutoring systems as design

To build intelligent tutoring systems (ITSs) is not easy. Over the years, various attempts had been made with many problems uncovered. This paper presents the situation and proposes the notion of ITS as design to engage ITS development with more rigor. With the various related issues, principles and characteristics of design described, the ITS design problem space is elaborated. Implications from adopting such a perspective, including (a) a systems approach to ITS, (b) a paradigm hierarchy, (c) the emergence of an agent model, and (d) the need for a description language, are highlighted. We further argue that by such a rendering, more systematic collection of efforts on ITS can be achieved. It is envisaged that the discussions would help set the research of ITS in context and provide further intuition towards ITS development.