Intelligent Tutoring System

1. INTRODUCTION
With the advancement in technology, computers have become es sential tools in developing systems that cater to the different needs of users. Currently, many works have been done in the field of education. Systems known as intelligent tutoring systems (ITS) were developed to teach students on specific topics, test their knowledge by giving exercises, and provide remediation on topics students did not perform well. An intelligent tutoring system is a computer program for educational support that can diagnose prob lems of individual learners. Such diagnostic capability enables it to adapt instruction or remediation to the needs of individuals. Currently, the state of ITS is focused on one-on-one learning instruction. However, in reality, students can also learn through interactions with his/her peers or work in a team (or a group). The information student receives from his peers can help improve his comprehension on the topics at hand. A new learning paradigm has emerged aiming on this area and this new learning paradigm is known as collaborative learning. Collaborative learning empha sizes on how students function in a group and how the student's interaction with his peers or work in a team can help improve students learning. This can be seen as either gaining new knowledge or verifying the correctness of what the students had learned so far. Meanwhile, one of the major issues in Distrib uted Artificial Intelligence involves multi - agency.

Intelligent Tutoring System The agents in a multi agent system are designed to solve a kind of problem. This is based on the fact that agents are autonomous and can recognize their own existence and the existence of other agents. Agents help each other in order to achieve a common purpose within a certain environment. Agents can assist each other by-sharing the computational load for the execution of subtasks of the overall problem, or through sharing of partial results that are based on somewhat different perspectives of problem solving on the overall. In the last half- decade, ITS have moved out from labs into classrooms and workplaces, where some have proven to be highly effective as learning aids.

Intelligent Tutoring System

2. LITERATURE REVIEW
Introduction to Intelligent Tutoring System: An intelligent learning environment is a relatively new kind of intelligent educational system, which combines the features of traditional Intelligent Tutoring Systems (ITS) and learning environments. Traditional ITS are able to support and control student's learning on several levels but doesn't provide space for student - driven learning and knowledge acquisition. An intelligent learning environment (ILE) includes special component to support student driven learning, the environment module. The term environment is used to refer to that part of the system specifying or supporting the activities that the student does and the methods available to the student to do those activities". (Burton, 1988, p. 109.) Some recent ITS and I L E include also a special component (we call it as manual '') which provides an access to structured instructional material. The student can work with the manual via help requests or via special browsing tools exploring the instructional material on her own. An integrated ILE, which includes the environment and the manual components in addition to regular tutoring component, can support learning both procedural and declarative knowledge and provide both system - controlled and student driven styles of learning. An ITS is really a knowledge communication system. It can be so defined because the main emphasis in the development of these systems is to provide them with access to a representation of the knowledge that the system

Intelligent Tutoring System then attempts to communicate to a student. In an ITS the emphasis is placed upon the knowledge (what) to be communicated and not on the mechanism (how) used to present the knowledge to the student.

User

User Interface

Interface Engine

Knowledge base

WHAT IS AN ITS?
ITS is a system that provides individualized tutoring or instruction. Each ITS must have these three components: knowledge of domain, knowl edge of the learner, and knowledge of teacher strategies. The domain refers to the topic or curriculum being taught. The learner refers to the student or the user of the ITS. The teacher strategies refer the methods of instruction and how the material shall be presented. This basic outline of requirements has been around since 1973 when it was introduced by Derek H. Sleernari and J.R. Hartley. The goal for every ITS is to communicate its embedded knowledge effectively.

Intelligent Tutoring System

HOW DOES IT WORK?

A student learns from an ITS by solving problems. The system selects a problem and compares its solution with that of the student and then it performs a diagnosis based on the differences. After giving feedback, the system reassesses and updates the student skill model and the entire cycle is repeated.

Intelligent Tutoring System

HOW ITS WORKS

In order to provide hints, guidance, and instructional feedback to learners, ITS systems typically rely on three types of knowledge, organized into separate software modules (as shown in Figure 1). The "expert model" represents subject matter expertise and provides the ITS with knowledge of what its teaching. The "student model" represents what the user does and doesn't know, and what he or she does and doesn't have. This knowledge lets the ITS know who it's teaching. The "instructor model" enables the ITS to know how to teach, by encoding instructional strategies, used via the tutoring system user interface.

Expert Model Simulation Instructor Model Tutoring System UI

Student Model

Figure 1: Components of an intelligent tutoring system Here's how each of these components works. An expert model is a computer representation of a domain expert's subject matter knowledge and

Intelligent Tutoring System problem-solving ability. This knowledge enables the ITS to compare the learner's actions and selections with those of an expert in order to evaluate what the user does and doesn't know. A variety of artificial intelligence (A!) techniques are used to capture how a problem can be solved. For example, some ITS systems capture subject matter expertise in rules. That enables the tutoring system to generate problems on the fly, combine and apply rules to solve the problems, assess each learner's understanding by comparing the software's reasoning with theirs, and demonstrate the software's solutions to the participant's. Though this approach yields a powerful tutoring system, developing an expert system that provides comprehensive coverage of the subject material is difficult and expensive. A common alternative to embedding expert rules is to supply much of the knowledge needed to support training scenarios in the scenario definition. For example, procedural task tutoring systems enable the course developer to Create templates that specify an allowable sequence of correct actions. This method avoids encoding the ability to solve all possible problems in an expert system. Instead, it requires only the ability to specify how the learner should respond in a scenario. Which technique is appropriate depends on the nature of the domain and the complexity of the underlying knowledge. The student model evaluates each learner's performance to determine his or her knowledge, perceptual abilities, and reasoning skills.

Intelligent Tutoring System Valerie Shute at the Air Force Research Laboratory presents the following simple example of a hypothetical arithmetic tutoring system. Imagine that three learners are presented with addition problems that they answer as follows:

Figure 2: ITS Student Modeling Example 22 S tu d e n t A +39 51 22 S tu d e n t B +39 161 22 S tu d e n t C +39 62 46 +37 73 46 +37 183 46 +37 85

Though all three participants answered incorrectly, different underlying misconceptions caused each person's errors. Student A fails to carry, Student B always carries (sometimes unnecessarily), and Student C has trouble with single-digit addition. In this example, the student supplies an answer to the problem, and the tutoring system infers the student's misconceptions from this answer. By maintaining and referring to a detailed model of each user's strengths and weaknesses, the ITS can provide highly specific, relevant instruction.

Intelligent Tutoring System

WHAT ITS MUST DO?

Although there are many types of Intelligent Tutoring Systems around, each one must behave intelligently, not actually be intelligent. They must be able to: accurately diagnose student's knowledge structures, skills, and styles diagnose using principles, rather than preprogrammed responses decide what to do next adapt instruction accordingly provide feedback.

Intelligent Tutoring System

BENEFITS OF INTELLIGENT TUTORING SYSTEMS

Intelligent tutoring system technology can make simulator - based or other active training courses even more effective with the following fea tures and benefits: Increases student / instructor ratio from around 1:1 to, perhaps, 10:1 or more, to reduce training costs enormously, and still deliver close to a one on - one learning experience. Shortens training time and / or improve skill level even further than simulator alone by individualizing instruction for each student. Automatically optimizes individual learning. Compensates for a shortage of expert instructors. Also enables quickly coping with sudden unanticipated upsurges in student enrollment, re ducing or eliminating the need to hire and train more instructors. Builds "student model" for each student, that includes: Performance on training exercises. Details of information / remediation received Details of knowledge mastered / failed / unknown / misunderstood. Performance on remediation activities. Student preferred learning style.

Intelligent Tutoring System Adaptively makes decisions on how to best teach each stu dent based on knowledge of student in student model", knowledge of principles to be taught and embedded teaching method. Present student with ap propriate simulation scenarios, descriptive material, or remediation material (including reruns of simulations) which the ITS intelligently and automati cally selects. Automatically assesses each student's actions, so an ITS can provide a full record of student performance on the simulator to: Aid instructor in helping student. Provide a permanent record of student's training performance. Aids and documents achievement of job mastery in critical skills. Reduce administrative work Adaptively improves its teaching style with each student the more the ITS works with a student. Provides each individual student with remediation in the spe cific fine details that are needed. Extensible to other applications besides education because of ability to monitor people doing things and summarize this information. E.g., could automatically assist on - the -job individual air traffic controllers oper ate their equipment under difficult circumstances by dynamically improving their interfaces and decision support software based on information about in dividual students gained by ITS during training.

Intelligent Tutoring System 11) Works on standard PCs and across the Web, and thus can in crease the effectiveness of distance learning. Enables the skills of a master instructor to be transferred to less experienced instructors via the default instructional methods that the master provides for a course of instruction in the software. Allows training to keep pace with rapidly changing technology, customization of products, and other sources of rapid change. An intelligent tutoring system can be guaranteed to stay with a student throughout the duration of a course and continue to learn about their Individual students; human instructors may not. 15) For team training, intelligent software agents can be substi tuted for real people.

Intelligent Tutoring System

AI & INTELLIGENT TUTORING SYSTEMS

In 1982, Sleeinan and Brown reviewed the state of the art in computer aided instruction and first coined the term Intelligent Tutoring Systems (ITS) to describe these evolving systems and distinguish them from the previous CA1 systems. The implicit assumption about the learner now focused on learning-by-doing. They classified the existing ITS as being computer-based (I) problem-solving monitors, (2) coaches, (3) laboratory instructors, and (4) consultants. (Sleeman & Brown, 1982) The emphasis in these systems was still as research platforms for refining Al theories, but now researchers were thinking about representing student knowledge within these systems. Here we find the first use of the term student model to describe an abstract representation of the learner within the computer program.

Early attempts to model student knowledge were based on a ''buggy" model first proposed by Brown and Burton (Brown & Burton, 1978). "Bugs" are student errors in discrete skills, such as incorrect carrying during subtraction. Burton elaborated on this model with the DFBUGGY system (Burton, 1982) DE8UGGY identified 130 "bugs" designed to account for mistakes in subtraction. The challenge was to analyze the problem space represented by the student's answers and determine which bug or set of bugs best accounted for incorrect subtraction.

Intelligent Tutoring System

Sleeman and Brown mention some learning issues related to the problems involved in creating ITS. The y ac knowledge that much human tutor communication is implicit and express the hope That ITS will provide a venue for educational theorists to develop "more precise theories of teaching and learning Their assumption is that such precision is possible, being necessary for implementation of these theories within computer software. They also discuss the need to construct environments that encourage collaborative learning while acknowledging that researcher, (at that time) knew little about how such cooperation takes place in natural learning settings.

Intelligent Tutoring System

ACT* Assumptions Principles Problem-solving goal driven behavior is structure

Corresponding

Tutoring

Communicate underlying the solving task

the

goal

problem-

Declarative

and

procedural

Represent

the

student's

knowledge are separate. The units of procedural knowledge are IF-THEN rules called productions. Initial performance of a task is accomplished by applying weak (general) procedures structures. Task-specific productions arise by applying weaker underlie productions more to declarative knowledge. These task-specific productions performance The student maintains the efficient to declarative knowledge

knowledge as a production set.

Provide instruction in the problem-solving context; let student's knowledge develop through successive approximations to the target skill. Adjust the step size of

instruction as learning progresses

Minimize working memory load

current state j of the problem in a limited capacity working memory

Table 1: ACT* assumptions and related principles for a computerimplemented tutor.

Intelligent Tutoring System Although Anderson and his colleagues created ACT* as a cognitive theory, they believed that it was rigorous enough to test by implementing the principles in computer software. Two of th e best-known examples are th e Geometry Tutor (koedinger & Anderson. 1993) and LISPITS (LISP Intelligent Tutoring System). The LISPITS system, a program for teaching LISP programming, .was designed to implement these principles in the context of "model tracing LISPITS attempts to model the steps needed to write a LISP program. The program th en compares the actual steps that the student takes with this model. Corbett and Anderson call the monitoring and remediation process knowledge tracing. Their goal is a mastery model, where every student masters 95% of the rules for a given set of exercises before moving to the next section. Corbett & Anderson found that students using LISPITS completed the mastery model exercises considerably faster than students who worked alone, but not as fast as students who worked with human tutors. Anderson's name has become synonymous with ITS work in so far as people often speak of "Anderson-style tutors" (Chipman, 1993) Perhaps this is because his systems are some of the few that have actually been used in classroom settings and were not solely research projects. Intelligent Tutoring Systems are built on a fairly well established architecture, which relies on three interconnected software modules: 1) 3) Expert Module, Curriculum module. 2) Student module

Intelligent Tutoring System

CONCLUSION

With the advancement in technology, computers have become es sential tools in developing systems that cater to the different needs of users. Currently, many works have been done in the field of education. Systems known as intelligent tutoring systems (ITS) were developed to teach students on specific topics, test their knowledge by giving exercises, and provide remediation on topics students did not perform well. An intelligent tutoring system is a computer program for educational support that can diagnose prob lems of individual learners. Such diagnostic capability enables it to adapt instruction or remediation to the needs of individuals. Currently, the state of ITS is focused on one-on-one learning instruction.

Intelligent Tutoring System

REFERENCES
www.google.com www.its.com

Intelligent Tutoring System

CONTENTS
Sr. No. 1) 2) 3) 4) 5) 6) 7) 8) 9) 10) Contents Page No. 1 3 4 5 6 8 9 10 17 18

INTRODUCTION LITERATURE REVIEW WHAT IS AN ITS? HOW DOES IT WORK? HOW ITS WORKS WHAT ITS MUST DO? BENEFITS OF INTELLIGENT TUTORING SYSTEMS AI & INTELLIGENT TUTORING SYSTEMS CONCLUSION REFERENCE