Mechanisms for ContextInformed Adaptive Hypermedia

1
Mechanisms for Context-Informed Adaptive
Hypermedia

• Alexander OConnor
• Supervisor Vincent Wade

2
Motivation

• Considerable valuable work in the areas of
  Adaptive Hypermedia1 and Context-Awareness
• Adaptive Hypermedia includes powerful techniques
  for modeling learner, content, etc
• Context Awareness concerned with translating a
  wide variety of inputs

? Can Context-Awareness techniques be used to
expand the power of Adaptive Hypermedia?
3
Overview

• Project Goals
• State of the Art
• Designing Context-Informed Adaptive Hypermedia
• Implementation
• Demonstration
• Evaluation
• Conclusions

4
Goals

• Overall Objective of the Project to discover a
  method to apply Context to Adaptive Hypermedia
• Three specific goals
• Survey of Context-Aware and Adaptive Hypermedia
  Systems.
• Design Mechanisms for applying Context to
  Adaptive Hypermedia
• Prototype and Test the design, evaluate the
  results

5
State of the Art

• Survey of Context-Aware Systems
• Survey of general definitions of Context
• Survey of Specific Context-Aware Systems
• Definition of Context
• Survey of Adaptive Hypermedia
• Survey of Specific Systems
• ?Identify Context in Adaptive Hypermedia

6
Context-Aware Systems

• Classified by three questions
• What is Context?
• Where can Context be used?
• Where can Context be gathered?
• 3 Systems reviewed
• ActiveCampus2
• Context-Aware User Authentication3
• MOBilearn4

7
Definition of Context

• The axes of knowledge which, though not defined
  a-priori, provide useful additional input to the
  core models of adaptivity

8
Adaptive Hypermedia Systems

• AHA!5
• Interbook6
• Knowledgetree7
• APeLS8

9
APeLS

• Multi-Model Adaptive Hypermedia
• Learner Model
• Content Model
• Content is grouped into Candidate Groups
• Narrative Constructs courses from Learners Goals

10
Adaptive Personalised eLearning Service (APeLS)
Architecture
Narrative Models
Content
Learner Models
11
Designing Context-Informed Adaptive Hypermedia

• Context must access all models, because it cannot
  be defined in advance
• Defined Ten Guiding principles
• Properties of Context or its use
• The basis for design and evaluation of the
  implementation

12
Guiding Principles

• Autonomy
• Simplicity
• Expressiveness
• Shared Knowledge
• Obfuscation
• Encapsulation
• Frequency
• Range
• Importance
• User Empowerment

13
Design

• Context Interpreter aggregates input and
  translates it to a known vocabulary
• Concepts and Content for the Adaptive Engine
• This is applied to the models of the Adaptive
  Engine
• 3 Mechanisms Defined

14
Adaptive Personalised eLearning Service (APeLS)
Architecture
Narrative Models
Content
Learner Models
15
Mechanisms

• User Model Update
• The Context Interpreter provides additional
  adaptivity information about the Learner
• Candidate Group Manipulation
• Context Interpreter selects Candidate Groups from
  a list provided
• Also used for Content Selection
• Narrative Choice
• Narrative defines decision points which are
  resolved by the Context Interpreter

16
Implementation

• Built on APeLS by KDEG
• Modification of courses already created
• Context Interpreter designed as web service using
  the Apache Axis package
• Simple Context Interpreter to provide tests
• Three Defined Scenarios
• High, Medium and Low Context

17
Low-Context Scenario

• Terminal Adaptivity
• Context Interpreter measures the capabilities of
  the Learners Terminal
• Maths Course Content Selection via Manipulation
• SQL Course User Model Enrichment for Candidate
  Group selection provide terminal class9

18
Mid-Context Scenario

• Broken Narrative Language Selection
• Context Interpreter selects between educationally
  similar course sections based on its knowledge
• SQL Course Implemented as Narrative Decision
  point
• SQL Course Implemented as User Model Enrichment
• Also Includes User Feedback

19
High-Context Scenario

• Anonymous User Recognition
• Context Interpreter provides the entire content
  of the Learner Model
• Maths Course Implemented using User update

20
Evaluation

• Different levels of Context reinforce that
  Context is a set of concerns that are not core,
  but that can be used to make core decisions
• Implementation evaluated against guidelines

21
Guiding Principles

• Autonomy
• Simplicity
• Expressiveness
• Shared Knowledge
• Obfuscation
• Encapsulation
• Frequency
• Range
• Importance
• User Empowerment

22
Conclusions

• Initial Investigation reveals promise
• Future work to develop Context Interpreter
• Correlation between Context and Adaptive Engine
• Ontology
• Expressing capabilities

23
References (I)

• 1 Brusilovsky, P. Methods and techniques of
  adaptive hypermedia. User Modeling and
  User-Adapted Interaction 6, 2-3 (1996), 87129.
• 2 Griswold, W. G., Boyer, R., Brown, S. W.,
  Truong, T. M., Bhasker,E., Jay, G. R., and
  Shapiro, R. B. ActiveCampus - Sustaining
  Educational Communities through Mobile
  Technology. UCSD CSE technical report
  CS2002-0714, Department of Computer Science and
  Engineering University of California San Diego,
  July 2002.
• 3 Bardram, J. E., Kjær, R. E., and Pedersen, M.
  Ø. Context-aware user authentication - supporting
  proximity-based login in pervasive computing. In
  Ubi-Comp 2003, the Fifth International Conference
  on Ubiquitous Computing (Seattle,Washington, USA,
  2003).
• 4 Lonsdale, P., Baber, C., and Sharples, M. A
  context awareness architecture for facilitating
  mobile learning. In MLEARN 2003 Learning with
  Mobile Devices (London, UK, 2003).
• 5 DeBra, P., Aerts, A., Berden, B., deLange,
  B., Rousseau, B., Santic,T., Smits, D., and
  Stash, N. Aha! the adaptive hypermedia
  architecture.In Proceedings of the fourteenth ACM
  conference on Hypertext and hypermedia (2003),
  ACM Press, pp. 8184.

24
References (II)

• 6 Brusilovsky, P., Eklund, J., and Schwarz, E.
  Web-based education for all a tool for
  development adaptive courseware. Computer
  Networks and ISDN Systems 30, 17 (1998),
  291300.
• 7 Brusilovsky, P., and Nijhavan, H. A framework
  for adaptive e-learning based on distributed
  re-usable learning activities. In Proceedings of
  World Conference on E-Learning, E-Learn 2002
  (Montreal, Canada, 2002), AACE, pp. 154161.
• 8 Conlan, O., Wade, V., Bruen, C., and Gargan,
  M. Multi-model, metadata driven approach to
  adaptive hypermedia services for personalized
  elearning. In Second International Conference on
  Adaptive Hypermedia and Adaptive Web-Based
  Systems (Malaga, Spain, 2002)
• 9 Dagger, D., Conlan, O., and Wade, V. Towards
  anytime, anywhere learning The role and
  realization of dynamic terminal personalization
  in adaptive elearning. In Ed-Media 2003, World
  Conference on Educational Multimedia, Hypermedia
  and Telecommunications (Hawaii, USA, 2003).

25
(No Transcript)