welcome to my website teaching online.net
Teaching Online Contents
- 1 Intelligent Tutoring Systems
- 2 What is ‘Intelligence’?
- 3 Structure of the Intelligent Tutoring System (ITS)
- 4 Domain Expertise Module
- 5 Student Module
- 6 Teaching Expertise/Pedagogical Module
- 7 Communication or Interface Module
- 8 Domain Knowledge Module
- 9 Explanatory Knowledge Module
- 10 Control Knowledge Module
- 11 Potentials of Intelligent Tutoring System
Intelligent Tutoring Systems
Intelligent Tutoring Systems are computer programmes that instruct the student in an intelligent way. They are designed to incorporate techniques from the artificial intelligence community to provide tutors to understand and know what they teach? To whom they teach? and how they teaching online? The goal of an Intelligent Tutoring System (ITS) is to apply Artificial Intelligence (Al) methods and techniques to develop highly individualized computer-based instructional environments in which the student and computer tutor can have a flexibility that closely resembles what actually occurs when student and human tutor sit down together i.e. one-on-one/ face- to- face and attempt to teach and learn together (Seidel & Park, 1994). Such flexibility is important because without it, during instruction the system cannot be fully adaptive to the individual student’s learning needs.
What is ‘Intelligence’?
How can a computer system be programmed to perform intelligently? This question drives the empirical and engineering research in a field called ‘Artificial Intelligence (Al)’. The simplest definition of AI is that “Artificial intelligence is the study of mental faculties through the use of computational models”. One of the main objectives of AI is designing and development of computer systems which can solve the same kinds of problems that we deem intelligent. On the basis of the above definition we can answer the question in Sharon ( 1993) words that what is the role of Intelligence in intelligent tutoring systems? “An intelligent instructional system can observe what the student is doing during problem solving and/ or has done over a series of problem-solving sessions and from this information draws inferences about the student’s knowledge, beliefs and attitudes i n terms of some theory of cognition”. A system can be intelligent whether or not it makes instructional decisions based on this information but, if it doesn’t use such information in instructional decision-making, then it cannot be categorized as an intelligent tutoring system, but rather a tool that has some diagnostic capabilities.
Gugerty (1993) with some more clarity defines that Intelligent tutoring involves:
1 explicit modeling of expert representations and cognitive processes;
2 detection of student’s errors;
3 diagnosis of student’s knowledge (correct, incorrect and missing);
4 instruction adapted to student’s knowledge state (via problem selection, hints, feedback and explicit didactic instruction and;
5 doing all of the above in a timely fashion as the student solves problems (not post hoc).
Seidel and Park (1994) described several intelligent features which are intrinsic to ITS, that are difficult or impossible to include in traditional CBI using ordinary programming techniques .Some of the main features are:-
- ITS can generate knowledge rather than selecting pre-programmed frames containing knowledge to present to the student spontaneously according to the student’s on-going needs during the learning process.
- ITS allows both the system and student to initiate instructional activities by applying AI techniques. This “mixed initiative” approach is an important intelligent feature to simulate the live (one-to-one) tutoring process.
- ITS can make inferences i n interpreting the student’s inputs, diagnosing misconceptions and learning needs and generate instructional presentations on the basis of what is available at that time.
- ITS can monitor, evaluate and improve its own performance by applying Al techniques commonly used in machine learning.
- Modeling of the student learning process and qualitative decision making of instruction are intelligent feature of ITS.
Structure of the Intelligent Tutoring System (ITS)
A typical ITS consists of the following major components or modules (Jerinic & Devedzic 2000) –
- Domain Expertise Module
- Student Module
- Teaching Expertise Pedagogical Module
- Communication Module
- Domain Knowledge Module
- Explanatory Knowledge Module
- Control Knowledge Module
Domain Expertise Module
In order to generate the information required by the student, the ITS (like a teacher) possesses the knowledge of the subject area or domain. The domain expertise module contains all the knowledge or subject matter in a knowledge base. This knowledge is to be represented in structures, which are understandable and can be manipulated by the computer system. Traditional CAL does not have expert modules of this sort because it is not required to actually solve the problems presented to students other than those solvable through algorithmic methods, i.e., mathematical problems. The difference becomes apparent in domains where heuristic reasoning on domain concepts is needed rather than execution of algorithms.
The student module is the component of an ITS that represents the student’s current state of knowledge. The role of the student module is to build up a picture of the student in terms of what the student knows and what does not know in order to provide him individualized instructions. It should infer what the student already knows about the subject matter and how well the student is progressing. This information is used to decide what next step in the sequence of knowledge should be presented to the student.
ITS attempts to capture the student’s profile while the student is interacting with the computer through a variety of parameters, i.e. type of information requested, speed of acquisition of information, response time, etc. The system then builds up a cognitive model of the student and model of the student’s views on the subject also called domain model. The cognitive model represents the general intellectual abilities of the student while the domain model represents the perception of the student about the discipline under study.
Teaching Expertise/Pedagogical Module
This module decides the teaching strategies to be used in imparting the instruction to a particular student, therefore, incorporates the knowledge regarding the pedagogical principles and practices. As teaching online is not merely an orderly presentation of the instructional material, it must use the knowledge about the learner capabilities from the student model and his/ her own goal structure to decide what instructional activities will have to be presented. It also decides to present new material or revise previously taught material. It decides itself when the student needs help and computer gives the appropriate help. Questions are asked, when this module decides that student should be tested and explanations are given to the student when it decides that the student is confused. Thus, this module designs and regulates the instructional interactions between student and computer.
Communication or Interface Module
This module is responsible for the interaction of computer with the student. Ideally, this interaction should be bi-directional and in natural language of the student. The conventional CAI system permits only limited communication from computer to student but the communication from student to computer is highly restricted or non-existent. But in CAL an effort has been made to give an opportunity to the student to improve his/her computer communication-skills. In communication module analyses, students’ questions/responses and presents the interpreted information to the CAL system. The teaching expertise module looks at this information and combines it with the information provided by the domain expertise module. Then on the basis of information Interface module, an instructor prepares the information to be provided to the student. This information is given to communication module, which transforms it into natural language and presents it to the student.
Domain Knowledge Module
Domain knowledge is represented using one or more knowledge representation techniques. In the most general case, domain knowledge is a structured record of many interrelated knowledge elements. These elements describe relevant domain models and heuristics and can vary a lot in their nature, complexity and representation. There can be everything from simple data to instantiated knowledge primitives such as frames, rules, logical expressions, procedures, etc; and even more complex knowledge elements represented using either simple aggregations of the knowledge primitives or conceptually different techniques based on the knowledge primitives and other knowledge elements. Semantic nets are the suggested kind for such complex knowledge. Thus, Domain Knowledge Module is frequently used for representing deep knowledge about the problem domain.
Explanatory Knowledge Module
The primary purpose of the part of the knowledge base that we refer to as the explanatory knowledge is to define the contents of explanations and justifications of the ITS learning process as well as the way it is generated. Explanatory knowledge is related to both – domain knowledge and control knowledge and often these two types of knowledge are a part of the other two components of knowledge bases.
Control Knowledge Module
In this module, the contents of the IT System’s control knowledge are – abstract, explicit and more or less domain independent descriptions of the way to learn some facts during the ITS is in operation.
Potentials of Intelligent Tutoring System
Intelligent Tutoring System (ITS) is a powerful teaching online and training tool with great potential and its implications are many faceted for the developing nations. The promise of IT is to reduce drastically the teaching time and to provide quality education. These may be exploited and there is a big challenge to prepare the manpower i n a cost effective way with limited national resources. IT system has the potential to give quality training to a large number of persons together. The system because of its ‘intelligence’ reduces the dependency upon the teachers and yet provides a good learning environment. IT system incorporates student centered interactive approach that may develop the abilities, such as -exploration, hypothesis formation, reasoning, questioning, etc. Thus, instead of merely transmitting the knowledge, the use of intelligent Tutoring System (ITS) is likely to promote scientific temper among learners and learn the things objectively without any prejudices or biased attitude rather than merely transmitting the information.