Prof. Dr. Mohamed M. El HadiSadat Academy for Management

Sciences

M. M. El Hadi1

Intelligent Tutoring Systems

OVERVIEW

M. M. El Hadi2

Introduction: Concepts, Objectives and Main Topics.

Learning Scenarios and Knowledge Representation

Factors Influencing ITSITS Conventional Model and Main

ComponentsCase Based Reasoning and ITSPerfect Teacher and ITSDevelopment Process to Create ITS

1. INTRODUCTION:What Are Intelligent Tutoring Systems?

M. M. El Hadi3

System that provides personalized tutoring by: Generating problem solutions automaticallyRepresenting the learner’s knowledge

acquisition processesDiagnosing learner’s activitiesProviding advices and feedback

Intelligent Tutoring Systems

M. M. El Hadi4

Traditional CAI Fully specified presentation textCanned questions and associated answersLack the ability to adapt to students

ICAI: intelligent computer-aided instructionReasoningRich representation of domainUser modelingCommunication of information structures

ITS - Objectives

M. M. El Hadi5

Practising environment (learn by doing)Provide useful feedback on a student’s

answer to a problemModel the content and the studentAllow to make inferences about a student’s

knowledge in order to adapt the content.

ITS Main Topics

M. M. El Hadi6

Learning ScenariosDomain Knowledge RepresentationStudent ModelingStudent DiagnosisProblem GenerationUser Interface

2. LEARNING SCENARIOSAND KNOWLEDGE REPRESENTATIONLearning Senarios

M. M. El Hadi7

The situation in which the student’s learning is to take place

Coaching: offer a student advice and guide him when misdirected

Gaming environment: combine both coaching and discovering learning

Socratic teaching methodSimulation-base trainingDiscovery learning

Knowledge Representation

M. M. El Hadi8

Knowledge is the key to intelligent behaviorThe form in which we store the knowledge is

crucial to our abilities to use itNo general form suitable for all knowledge

Challengedetermine the type of knowledge required,

and suitable representation for that knowledge, to support teaching particular subjects

Script Representation

M. M. El Hadi9

WHY, a Socratic tutoring systemTest student’s understanding of the major

casual factors involved in rainfallRequire a representation with different levels

of abstractionScript

Nodes represent processes and events, links represent such relations as X enables Y or X causes Y

Each node have a hierarchically-embedded subscript

Roles are bound to geographic or meteorological entities in a particular case

Semantic Network

M. M. El Hadi10

SCHOLARA mixed-initiative, fact-oriented systemRequires a highly-structured data base in

which concepts and facts are connected along many dimensions

Semantic networkNodes and links represent objects and

propertiesGenerate questions, answers, errors and

branching information from the semantic network of knowledge

Support flexible query and reasoning

Knowledge Representation Techniques

M. M. El Hadi11

SCHOLARA mixed-initiative, fact-oriented systemRequires a highly-structured data base in

which concepts and facts are connected along many dimensions

Semantic networkNodes and links represent objects and

propertiesGenerate questions, answers, errors and

branching information from the semantic network of knowledge

Support flexible query and reasoning

3. FACTORS INFLUENCING ITSStudent Modeling

M. M. El Hadi12

Overlay Modelingstudent’s knowledge is viewed in terms of

the tutor’s domain knowledgeSeveral approaches

Semantic net with nodes and links are added as they are taught

Stars with the expert knowledge base and annotates deviations that are subsequently discovered

Skill modeler: student modeled by the set of skills he has mastered

Buggy Model

M. M. El Hadi13

Fact: the novice’s error can not be explained by the expert’s knowledge

Buggy model employs both correct and “buggy” rules

To understand an error, a combination of these correct and buggy rules has to be found to produce the same incorrect answer

Student Diagnosis

M. M. El Hadi14

Buggy modelProcedural networks: partially-ordered

sequences of operationsAnswer is evaluated by search for a path

through this network of skillsProblem:

The number of paths grows exponentiallyRequire an explicit enumeration of bugs

Student Diagnosis (Cont.)

M. M. El Hadi15

Error taxonomyThe knowledge of the types of

misconceptions in a particular domainObject-oriented approach

Each knowledge class inherits diagnostic capabilities from a particular Diagnoser class

Problem Generation

M. M. El Hadi16

A tree-structured decision processEach level represents another decision on

what to include in the problemEach branch represents one alternativesThe branches can be augmented with

probabilitiesSemantic net

Encode the types of objects and relevant attributes of these objects

A generative procedure fill in the particulars of the problem

Problem Generation (Cont.)

M. M. El Hadi17

Problem generation, expert problem solving and student diagnosis can be viewed as a set of constraints on their solution

We can evaluate student answers by checking that al constraints are satisfied

Give student feedback on wrong answers by telling him which constraints he failed to satisfy

User Interface

M. M. El Hadi18

Text generation in tutoring systemsMost avoid true natural language mechanisms

SCHOLAR incorporate rich natural language in two distinct levels: semantic and syntactic

User Interface (Cont.)

M. M. El Hadi19

Natural language parsingRich natural language facilities

Semantic grammars: look for understandable fragments in the input

Using graphical or menu-based input

4 .ITS CONVENTIONAL MODEL AND MAIN COMPONENTS

M. M. El Hadi20

The Three Main Components of an ITS

M. M. El Hadi21

The Student Model

The Pedagogical or Tutor Model

The Domain Knowledge

ITSs and Their Interaction

M. M. El Hadi22

The Student Model

M. M. El Hadi23

Keeps track of all information related to the learner :

Description of student behavior with regard to a specific problem

Performance concerning the material being taught

MisconceptionsKnowledge gap

Keeps track of all information related to the learner :

Description of student behavior with regard to a specific problem

Performance concerning the material being taught

MisconceptionsKnowledge gap How long

should we keep the

information?

How long should we keep the

information?

The Tutor Model

M. M. El Hadi24

Information about the teaching process:

When to review ? When to present new topics? What topics to teach?

Get input from the Learner model to make its decision to reflect the differing needs of each student.

The Domain Knowledge

M. M. El Hadi25

Contains the information the tutor is teaching

Most important part of the ITS

Issues:How to represent knowledge so it easily scales

up to large domain? How to represent domain knowledge other than

facts and

5. CASE-BASED REASONING (CBR)AND CBITS

M. M. El Hadi26

To represent the Student model and Domain Knowledge

There are different sources to obtain cases:

o Produced by the learner himselfo Experience from other learnero On-demand case generationo Predefined cases given by human tutors

Concepts of CBITS

M. M. El Hadi27

Where CBR technique become useful ?

oDuring the Problem Solving phase : Find similar problem solved in the past to provide learner with past experience feedback.

oCase-Based Adaptation

oCase-Base Teaching

Case Based Adaptation

M. M. El Hadi28

Where CBR technique become useful ?

oDuring the Problem Solving phase : Find similar problem solved in the past to provide learner with past experience feedback.

oCase-Based Adaptation

oCase-Base Teaching

Case-Based Teaching (Cont.)

M. M. El Hadi29

Main goal is to provide learners with useful information (in order to understand new topics and to help during the problem solving phase).

Case-Based Teaching system are either:oStatic (use given case base)oAdaptive (learn new case from learner

experience)

Different Types of Case-Based Reasoning

M. M. El Hadi30

Different type of CBR methods:

Classification Approach (used to provide help on well known pre-analyzed cases)

Problem Solving Approach (to diagnose solution proposed by the learner and to identify the problem solving path used)

Planning Approach (to support planning in the system)

Case Representation

M. M. El Hadi31

As a Complete case: Problem definition + detailed solution

As Partial Case (Snippet) : Subgoals of problems + solution within different contexts

CBITS In Real Life

M. M. El Hadi32

CBITS have been used in many different areas:

o Biology : INVISSIBLE (under construction)o Physics : ANDESo Math : ActiveMATHo Jurisprudenceo Economics

The most popular ones are: o Programming : ELM-Art, SQL-Tutor,o Chess : CACHET

But Why?But

Why?

Further Work of CBITS

M. M. El Hadi33

Reduce development time and cost:

Using Authoring tools (API that would simplify programmer’s task to represent knowledge and teaching strategies)

Using Modularity of the student, tutor and domain models for future reuse

Collaborative Learning Allowing student to interact (help) with each other

while learning with an ITS But problem concerning modeling student knowledge

and defining teaching strategies

SQL-Tutor

M. M. El Hadi34

Developed in 1996 by Dr. Mitrovic from University of Canterbury, New-Zeland.

Provide a good “on-hand” practice to student discovering SQL

Teaching with example and built-in Database relations.

Useful feedback is given by the system

SQL-Tutor (Cont.)

M. M. El Hadi35

Current State of Intelligent Tutoring

M. M. El Hadi36

• ITS failed to recognised the fact that knowledge has contextual component (everything does not work everywhere).

• Natural intelligence of student is ignored.

• ITS attempted to replace human teacher!

Attempts to create a perfect teacher rather than a teacher’s tool.

6 .PERFECT TEACHER AND ITS

M. M. El Hadi37

Different roles of teacher:

• ITS designer teacher

• ITS implementer teacher

(personality attributes, styles, preferences …)

Many implementer teachers distrust ITS as employing beliefs of the ‘designer teacher

Participants of ITS

M. M. El Hadi38

ITS is a joint cognitive system (Dalal & Kasper, 1994) involving:

• a tutoring software

• a student, and

• an implementing teacher.

Tutoring software contains attributes from designer teacher.

Context of ITS

M. M. El Hadi39

Student

EnvironmentalContexts

ITS

InteractionalContexts

Teacher

Teachingprocess

Assessmentprocess

ObjectivalContexts

Besides the interactional context, the environmental and objectival contexts are important for any

educational system.

Teacher and ITS

M. M. El Hadi40

Teacher as an Implementer of ITS

M. M. El Hadi41

• provides context (background, culture, policies..)

• selects and schedules other educational technologies

• manages the curriculum, and

• oversees the learning progression.

In the ensuing power relationship, tutor’s preferences may be more important than the

learning styles of a student!

Teacher as an Implementer of ITS (Cont)

M. M. El Hadi42

Different teaching styles may result in points of divergence within the joint cognitive learning.

Clark (in press) notes: Instructional methods, not the media cause

learning. Human brain can be overloaded by technologically

delivered sensory output.

However, the situation is not so straight forward!

Teacher as an Implementer of ITS (Cont)

M. M. El Hadi43

Novice learners may benefit from richer content, but may also get distracted without directed learning.

Different teachers would constrain the learning process in different ways reflecting their

teaching styles!

Where does the role of teacher fit in overall environmental context of ITS?

Environmental Context of ITS

M. M. El Hadi44

Teacher as an Environmental Context

M. M. El Hadi45

• Implementer Teacher provides power relationship.

• Preferences of a teacher prove to be more important than learning styles of students.

• Human teacher plays very important role in the acceptance of a tutoring system.

• Designer Teacher needs to take into account of implementer teacher’s preferences!

Modeling Human Teacher

M. M. El Hadi46

Human teachers may have:

• different personalities

• different teaching styles (born out of their traditional, progressive or vocational outlook and their own learning style)

• It is not possible to envisage all the preferences of implementer teacher at

design time.

Human Teacher Model

M. M. El Hadi47

We recommend a re-configurable human teacher model to be incorporated in the design of ITS:

• to recognise the different teaching styles

• to put on record the teaching style(s) adopted in the design, and

• enable manual or automatic adaptation to suit the implementing teacher

Why Explicit Record of Designer’s Teaching Style (s)

M. M. El Hadi48

• Better understanding of designer’s rationale by implementing teacher

• Help in dealing with the cognitive dissonance arising from any differences in teaching styles

Why Explicit Record of Designer’s Teaching Style (s) Cont.

M. M. El Hadi49

• Clear rationale behind adopted teaching strategy may also help in the student learning in less adaptive systems

• Easier understanding of representations which are difficult due to cultural differences

• If designer’s teaching style is unproductive in a culture, the system may be localised

ITS Incremental Growth

M. M. El Hadi50

• ITS, in their current stage, cannot replace all the functions of human teacher.

• Efforts should be on increasing productivity (just like initial word processors for steno-typists).

• ITS designers should treat human teacher as their target user.

• Human teacher model is next logical approach in that direction.

7 .DEVELOPMENT PROCESS TO CREAT ITS

M. M. El Hadi51

Select Domain

Choose Learning

Environment

Choose ITS Model

Interface Learning Environment and

ITS

Author ITSCreate Problems

Validate ITS Deploy ITS

Evaluate ITS

Main Stages of ITS Development Process

M. M. El Hadi52

Phase 1: Select Domain:

- Choose domain where problem solving plays a major role.

- Building an ITS requires high investment of efficient developers and their expertise.

Phase 2: Choose ITS Model

- Most popular models are cognitive tutors (Model Tracing, Knowledge Tracing) [Developed by Carnegie Mellon University, Pittsburgh, PA] and Constraint Based Tutor [Developed by Conterbury University, New Zeland]

- Choose CT to teach procedural skills.

- Choose CBT to teach open-ended domains.

Main Stages of ITS Development Process (Cont.)

M. M. El Hadi53

Stage 3: Choose Learning Environment: - Student interface has to be simple and adapted to the

domain (reduce memory load, motivate, etc.)

- A lot of learning environments exist already and can be reused)

Stage 4: Interface Learning Environment (LE) and ITS:

- Convert solution from learning environment into format required by ITS.

- Possibly integrate LE into ITS to make it Web accessible.

- Convert student solution to the XML web language format required by ITS.

- Convert Java language application to Java applet required by Web

Main Stages of ITS Development Process (cont.)

M. M. El Hadi54

Stage 5: Author ITS: - Existing ITS Examples: * WETAS: a development environment authoring tool

done through text files. WETAS is a domain model (knowledge base)

* ASPIRE: a deployment environment authoring tool (ASPIRE Tutor). It guides author in the development process and considered a semi-automated process for building the domain model.

- Constraint Based Tutor Model domain with constraints * IF X (relevance condition) is true Then Y (satisfaction condition) has to be also true - Feedback generated when: * Relevance condition is true * satisfaction condition is false

Main Stages of ITS Development Process (cont.)

M. M. El Hadi55

Stage 6: Validate ITS: - Test the knowledge base (constraints)

- Test if generated feedback is appropriate.

Stage 7: Deploy ITS: - Make ITS available to students

Stage 7: Evaluate ITS: - Identify aspects to be evaluated (example: effectiveness of the

feedback).

- Use real students learning the domain

- Pre- and post – test

- Comparison group (uses full version of ITS)

- Control group (uses version with no feedback).