Adaptive Learning Systems

Associate Professor Kinshuk

Information Systems Department Massey University, Private Bag 11-222 Palmerston North, New Zealand Tel: +64 6 350 5799 Ext 2090 Fax: +64 6 350 5725 Email: [email protected] URL: http://fims-www.massey.ac.nz/~kinshuk/

Introduction
Adaptive learning systems with particular focus on cognitive skills Accommodation of both the instuction and construction of knowledge Design based on informed educational methodologies

What exactly we mean by Adaptivity in Adaptive Learning Systems?

Intelligence/adaptivity
Increased user efficiency, effectiveness and satisfaction by Improved correspondence between learner, goal and system characteristics
4

Need of Intelligence/adaptivity
 Users generally work on their own without external support.  System is used by variety of users from all over the world.  Customised system behaviour reduces meta-learning overhead for the user and allows focus on completion of actual task.
5

Adaptable Systems
Systems that allow the user to change certain system parameters and adapt the system behaviour accordingly.

Adaptive Systems
Systems that adapt to the users automatically based on systems assumptions about user needs.
6

How does adaptivity work?

 System monitors users action patterns with various components of systems interface.  Some systems support the user in the learning phase by introducing them to system operation.  Some systems draw users attention to unfamiliar tools.  User errors are primary candidate for automatic adaptation.
8

Levels of adaptation
 Simple: hard-wired  Self-regulating: monitors the effects of adaptation and changes behaviour accordingly  Self-mediating: Monitors the effects of adaptation on model before putting into practice  Self-modifying: Capable of chaging representations by reasoning about the interactions
9

Problems in adaptation
 User is observed by the system, actions are recorded, giving rise to data and privacy protection issues.  Social monitoring becomes possibility.  User feels being controlled by the system.  User is exposed to adaptation concept favoured by the designer of the system.  User may be distracted from the task by sudden automatic modifications.
10

Recommendation for adaptive systems

 Means for user to (de)activate or limit adaptation procedure  Offering adaptation in the form of proposal  User may define specific parameters used in adaptation  Giving user information about effects of adaptation hence preventing surprises  Editable user model
11

Domain competence And computers

12

Constituents of Domain Competence

Easier to learn from mistakes
Action oriented and experiential Reflection oriented and abstract

Know-how

Know-why

Difficult to learn from mistakes

Know-why-not

Trial and error

logical processes

Know-how-not Know-when
An example of the know-how aspect of know-when is the temporal context required for an appropriate sequence of operation

Know-when-not
Context oriented and both experiential and abstract

An example of the know-why aspect of know-when is the environmental and behavioural contexts required for making a decision

Know-what Know-about
Awareness oriented 13

Constituents of Domain Competence

Know-how It has an operational orientation. It is mainly action-driven and hence predominantly experiential. It is difficult to inherit it from someone elses experience. Know-how-not Learning by mistakes. Examples : Computer simulation and virtual reality
14

Constituents of Domain Competence

Know-why It has a causal orientation. It is mainly reflection-driven and therefore based on abstraction. It can be inherited from someone elses line of reasoning. Know-why-not Logical processes. Needs deeper reflection.
15

Constituents of Domain Competence

Know-when (and -where) It has a contextual orientation. It provides the temporal and spatial context for both the know-how and know-why. It is thus both action and/or reflection driven.

16

Constituents of Domain Competence

Know-about It has an awareness orientation. It includes above three types of knowledge in terms of know-what. It also contains information about the environmental context of this knowledge.

17

Instruction in knowledge context

Ideally, an instructional system, designed for novice users, teach all knowledge constituents. But, know-why is difficult to handle mainly for two reasons: 1. It needs natural language interaction. 2. It needs use of metaphors, which are difficult to understand for a novice user. Know-how, on the other hand, is operational, and can be conveyed to the user more easily, even with symbolic representations.
18

Instruction in knowledge context

Traditional hypermedia based ITSs approach, in general, has been to teach the know-why aspect of knowledge with the help of explanations. The links provide stimulus to the user to know more about a particular topic. System works more as a friendly librarian and learning depends on the initiative of a student.

19

Theoretical framework best suitable for facilitation of cognitive skills?

Cognitive Apprentice Framework

20

Cognitive apprenticeship framework



Modelling: Learners study the task pattern of experts to develop own cognitive model Coaching: Learners solve tasks by consulting a tutorial component of the environment Fading: Tutorial activity is gradually reduced in line with learners improving performance and problem solving competence
21

Phases of Cognitive apprenticeship

1.

World knowledge (initial requirement) Observation of interactions among masters and peers Assisting in completion of tasks done by master Trying out on own by imitating

2.

3.

4.

22

Phases of Cognitive apprenticeship

5.

Getting feedback from master Getting advise for new things on the basis of results of imitation, comparing given solution with alternatives Reflection by student, resulting from masters advice

6.

7.

23

Phases of Cognitive apprenticeship

8.

Repetition of process from 2 to 7  Fading out guidance and feedback  Active participation, exploration and innovation come in Assessment of generalisation of the tasks and concepts learnt during repetition process

9.

24

Example system

Cognitive apprenticeship based learning environment (CABLE)

25

CABLE objectives
Environment should facilitate:


acquisition of basic domain knowledge; application of the basic domain knowledge in non-contextual and contextual scenarios to get skills of the discipline; and generalisation of the domain knowledge to get competence of applying it in real world situations.
26

CABLE architecture


Observation - for acquisition of concepts Simple imitation - skills acquisition through articulation of concepts Advanced imitation - generalisation and abstraction of already acquired concepts and for acquisition of skills of applying concepts in different contexts

27

CABLE architecture


Contextual observation - deeper learning after imitation process results into the identification of gaps in learners current understanding of the domain knowledge Interpretation of real life problems - for acquiring competence in such narrative problems as encountered in real life situations

28

CABLE architecture


Mastery in skills - for repetitive training Assessment - for measurement of overall progress

29

CABLE
System generated problems - random selection of variables Teacher generated Teacher generated Teacher generated rich contextual problems for contextual problems narrative problems with model strongly situated for generalised answers to simulate real life learning & testing learning & testing conditions

Intelligent Tutoring Tools

Tools of the Trade Assessment

Listen/ Observe Interactive Learning Domains Rehearsing/repairing concepts and misconceptions and their purpose missing concepts
Instruction as the main source

Testing Abstract or Single context

Testing Extending Multiple contexts Greater complexity and/or Building skills in Rich narrative the use of tools
Ensures generalisation and far transfer of knowledge

Learning by syntactic mapping of interface objects is possible

Descriptive text, illustrations and solved examples

Use of fine-grained interfaces

Fine-grained dynamic feedback

30

Why ? explanation for the system recommended solution

What did I do ? diagnostic feedback

Intelligent Tutoring Tools Structure

A network of inter-related variables where the whole network remains constant. Example, partial network of 7 out of a total of 14 variables in marginal costing.

31

Marginal costing relationships

R
R = VT + CT R=Q*P

VT
P=R/Q P =VU + CU

VT = R - CT VT = Q * VU

CT

CT = R - VT CT = Q * CU

P Q

Q = VT / VU Q = CT / CU Q=R/P CU = CT / Q CU = P - VU

VU
VU = VT / Q VU = P - CU

CU
32

Structure of an ITT
Knowledge Base 1. Variables 2. Relationships 3. Tolerances Modes - Student - Lecturer - Administrator Expert Model 1. Correct values 2. Derivation procedure Tutoring Module

Inference Engine
Random Question Generator Dynamic Messaging System

(Local expert model)

Student Model 1. Student input 2. Value status (filled or blank) 3. Derivation procedure 4. Interface preferences

Feedback (four levels)

File Management
Marker Lecturers model answer to any lecturer generated narrative questions (Remote Expert Model)

Input (student answer, position) Context based User Interface link to textual module description
Add-ons 1. Calculator 2. Table Interface }Application specific 3. Formula Interface 33

Tutoring Strategy of an ITT

 Introduction of complexity in phased manner  Corrective, elaborative and evaluative aspects of student model are used for tutoring.  Learning process is broken down to very small steps through suitable interfaces.  Road to London paradigm is adopted to eliminate the need for diagnostic, predictive and strategic aspects.
34

CABLE

Demo

Future work on mental process modelling

35