Adaptive Hypermedia 2ID20 Course 1

1
Adaptive Hypermedia 2ID20Course 1

• Dr. Alexandra Cristea
• a.i.cristea_at_tue.nl
• http//wwwis.win.tue.nl/alex/

2
Outline

• Adaptive Hypermedia of the Past, Present and
  Future
• Example systems and applications
• AH Reference architectures AHAM
• Authoring for Adaptive Hypermedia
• AH Authoring reference architecture LAOS
• A closer look on adaptation design LAG
• Learning Styles in Adaptive Hypermedia
• Authoring system MOT
• Delivery System AHA!
• Conclusions

3
1. Adaptive Hypermedia of the Past, Present and
Future

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

4
1. Adaptive Hypermedia of the Past, Present and
Future

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

5
(No Transcript)
6
Hypermedia

• information supported by different media and
  structured according to the hypertext principle.
• hypertext multimedia

7
Multimedia

• more than one media can be used
• e.g., video, sound and text, interactive
  application

8
Hypertext

• classical text - articulated info
• introduction, augmentation, conclusion.
• Hypertext allows access to different info in a
  non-linear way.
• Hypertext nodes links.
• nodes (pages) textual info
• links allow the user to activate other pages.

9
Back to hypermedia

• In Hypermedia every piece of information can
  be, at the same time, center and periphery,
  introduction and conclusion, important and
  unimportant according to the knowledge, interests
  and navigational choices operated by the user.
• Hypermedia differs from hypertext in the nodes
  contents
• not only text data, but also multimedia data.

10
What is Adaptive Hypermedia?

• Hypermedia
• different media types used in a single
  application (text, images, sound, video, )
• non-linear structure with navigation through
  hyper-links
• Adaptive
• application forms a model of the context in which
  it is used (user, place, time, device, etc.)
• application adapts to that context (can show
  different information, different media, different
  links, etc.)
• adaptation and user modeling interact with each
  other (or else we say the application is
  adaptable, not adaptive)

11
Index

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

12
The need for personalization
13
Why AH?

• Problems with hypermedia applications
• navigational freedom which links are relevant
  (for this user) ?
• comprehension what has the user seen before when
  reaching a certain node?
• presentation what fits the users screen? how
  much network bandwidth and processing power is
  available?

14
Why AH?

• Opportunities with adaptive hypermedia
• guide users towards relevant information (users
  can reach relevant information more easily and
  more quickly)
• make sure users can understand the presented
  information
• change the presentation so that it fits the
  users platform and environment

15
Why Adaptive Hypermedia?

• Problems with (non-adaptive) hypermedia
• authoring hypermedia is difficult because of the
  navigational freedom of end-users
• using hypermedia is difficult because the author
  did not anticipate the path the end-user follows
• using hypermedia is also difficult because it is
  easy to get lost in hyperspace
• Solutions through adaptive hypermedia
• compensate for unexpected comprehension problems
  due to the chosen navigation paths
• warn users before following links that lead to
  problematic navigation paths
• offer orientation support using adaptive overviews

16
Index

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

17
Application areas AH

• Many application areas
• thus very different systems?
• Educational hypermedia (course texts)
• On-line information systems
• On-line help systems
• Information retrieval hypermedia
• Institutional (or corporate) hypermedia
• Personalized views

18
Application Areas

• Educational hypermedia systems
• on-line course text, with on-line multiple-choice
  or other machine-interpretable tests
• On-line information systems
• information kiosk, documentation systems,
  encyclopedias, etc.
• On-line help systems
• context-sensitive help, (think of Clippy)
• Information retrieval and filtering
• adaptive recommender systems
• etc.

19
Adaptive Educational Hypermedia

• Origin Intelligent Tutoring Systems
• combination of reading material and tests
• adaptive course sequencing, depending on test
  results
• In Adaptive Educational Hypermedia
• more freedom for the learner guidance instead of
  enforced sequence
• adaptive content of the course material to solve
  comprehension problems when pages or chapters are
  read out of sequence
• adaptation based on reading as well as tests

20
Adaptive On-line Information Systems

• Examples encyclopedia, documentation, but also
  shopping sites, airline reservation, etc.
• goal provide information about different topics
• users are only interested in a few topics, not in
  studying the entire hyperspace
• the system needs to know the users goal(s) in
  order to adapt (goal can be a topic, a product,
  an airline trip)
• the system also needs to adapt to the users
  knowledge and background, perhaps also location
  (e.g. departing city)
• users need help most when the concepts they want
  do not match the concept structure of the
  application (e.g. they dont know a close airport
  to the destination of their trip)

21
Adaptive On-line Help Systems

• Like on-line information systems, but
• not independent but tied into an application (and
  called from that application)
• (part of) the context is known through the
  application
• often this context is the only information about
  the user needed to adapt the information
• hyperspace is reasonably small
• unfortunately adaptation does not turn bad help
  information into good, and it cannot compensate
  for missing help information
• popular (bad) examples Windows troubleshooter,
  Clippy

22
Adaptive Information Retrieval/Filtering

• Adaptive Retrieval
• adaptively refine search requests
• adaptively filter out non-relevant search results
• update user model based on implicit or explicit
  relevance feedback
• context information to be used can be a task,
  perhaps from a workflow system
• Adaptive Filtering
• filters incoming information without the user
  explicitly asking for it
• a personalized view interface for the Web can
  also be viewed as a filter
• relies on relevance feedback to form and update a
  user model

23
Index

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

24
Traditional Hypermedia
Document2 Text Pictures Link1
Document1 Text Pictures Link1 Link2
Document3 Text Pictures
25
Adaptation on Trad. Hypermedia
Document2 Text Pictures Link1
Show text document 1
Document1 Text Pictures Link1 Link2
Document3 Text Pictures
26
Adaptation on Trad. Hypermedia
Document2 Text Pictures Link1
Dont show text document 1
Document1 Text Pictures Link1 Link2
Document3 Text Pictures
27
Adaptation on Trad. Hypermedia
Document2 Text Pictures Link1
Show link(s) document 1
Document1 Text Pictures Link1 Link2
Document3 Text Pictures
28
Adaptation on Trad. Hypermedia
Document2 Text Pictures Link1
Dont show link(s) document 1
Document1 Text Pictures Link1 Link2
Document3 Text Pictures
29
What can be adapted? classical views

• Adaptive presentation
• change which information is shown
• change how that information is shown
• Adaptive navigation support
• change which links are shown
• change how these links are shown
• change the link destinations

30
What Do We Adapt in AH?

• Adaptive presentation
• adapting the information
• adapting the presentation of that information
• selecting the media and media-related factors
  such as image or video quality and size
• Adaptive navigation
• adapting the link anchors that are shown
• adapting the link destinations
• giving overviews for navigation support and for
  orientation support

31
(No Transcript)
32
Adaptive Presentation
33
Adaptive Navigation Support
34
Adaptive presentation

• The content of what is seen on the screen can be
  adapted according to current users model status.
  
• e.g., a qualified user can be provided with more
  detailed and deep info while a novice can receive
  additional explanation.

35
Content adaptation types

• Additional (or prerequisite or comparative)
  explanations Under a given set of circumstances
  some additional content is presented.
• Explanation variants Different versions of an
  explanation exist and are selected depending on
  the user.
• Sorting The most relevant information for a user
  is presented first.

36
Canned Text Adaptation

• Inserting/removing fragments
• prerequisite explanations inserted when the user
  appears to need them
• additional explanations additional details or
  examples for some users
• comparative explanations only shown to users who
  can make the comparison
• Altering fragments
• Most useful for selecting among a number of
  alternatives
• Can be done to choose explanations or examples,
  but also to choose a single term
• Sorting fragments
• Can be done to perform relevance ranking for
  instance

37
Example from 2L690

• Before reading about Xanadu the URL page shows
• In Xanadu (a fully distributed hypertext
  system, developed by Ted Nelson at Brown
  University, from 1965 on) there was only one
  protocol, so that part could be missing.
• After reading about Xanadu this becomes
• In Xanadu there was only one protocol, so that
  part could be missing.

38
Canned Text Adaptation (cont.)

• Stretchtext
• Similar to replacement links in the Guide
  hypertext system
• Items can be open or closed system decides
  adaptively which items to open when a page is
  accessed
• Dimming fragments
• Text not intended for this user is de-emphasized
  (grayed out, smaller font, etc.)
• Can be combined with stretchtext to create
  de-emphasized text that conditionally appears, or
  only appears after some event (like clicking on a
  tooltip icon)

39
Adaptive navigation support

• Guidance methods
• Global guidance methods
• Local guidance methods
• Orientation support methods
• Global orientation support
• Local orientation support

40
Link adaptation types

• Direct guidance Next button.
• Restricting access
• Removing, disabling, hiding.
• Sorting and presenting the most relevant or most
  ready to be learned links first.
• Annotation (colour)
• Map adaptation techniques

41
Adaptive Navigation Support

• Direct guidance
• like an adaptive guided tour
• next button with adaptively determined link
  destination
• Adaptive link generation
• the system may discover new useful links between
  pages and add them
• the system may use previous navigation or page
  similarity to add links
• generating a list of links is typical in
  information retrieval and filtering systems

42
Adaptive Navigation Support (cont.)

• Adaptive link annotation
• all links are visible, but an annotation
  indicates relevance
• the link anchor may be changed (e.g. in color) or
  additional annotation symbols can be used
• Adaptive link hiding
• pure hiding means the link anchor is shown as
  normal text (the user cannot see there is a link)
• link disabling means the link does not work it
  may or may not still be shown as if it were a
  link
• link removal means the link anchor is removed
  (and as a consequence the link cannot be used)
• a combination is possible hidingdisabling means
  the link anchor text is just plain text

43
Example from Interbook
4

3
2
v
1
1. Concept role 2. Current concept state
3. Current section state 4. Linked sections state
44
Adaptive Navigation Support (cont.)

• Map adaptation
• complete (site)maps are not feasible for a
  non-trivial hyperspace
• a local or global map can be adapted by
  annotating or removing nodes or larger parts
• a map can also be adapted by moving nodes around
• maps can be graphical or textual
• adaptation can be based on relevance, but also on
  group presence

45
Conclusion What is adapted?

• Adaptation is regarded as personalized views
  (navigational and presentational) over an
  objective Ontology created by the author and
  defined in a Conceptual Model.

46
Adaptive vs. adaptable
personalized
adaptive
adaptable
System-tuned
User-tuned
47
Adaptivity vs. adaptability

• An adaptable system provides users with options
  (tuners / handles) of determining some
  alterations to aspect, contents or functionality
  of the system, according to their preferences.
• An adaptive system adapts to the new conditions
  (usually deduced from a user model) automatically.

48
Gerhard Fischer 1 HFA Lecture, OZCHI2000
49
A Comparison between Adaptive and Adaptable
Systems
Gerhard Fischer 1 HFA Lecture, OZCHI2000
50
Index

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions

51
Adapt to what?

• User ? user model (UM)
• Goals ? ??
• Domain ? domain model (DM)
• Media ? presentation model (PM)

52
First Non-UM
53
Adapt to what?

• Goal local and global
• Goal is the answer to the question Why is the
  user using the hypermedia system and what does
  the user actually want to achieve?
• Goals can be local or global. Local goals may
  changed quite often. For example, the
  problem-solving goal is a local one, which
  changes from one educational problem to another
  several times within a session. Global goal can
  be the users learning goal.

54
Adapt to what?
Domain model properties
Adapt to
55
Adapt to what?

• Context / environment
• aspects of the users environment, like browsing
  device, window size, network bandwidth,
  processing power, etc.

56
Adapt to what?
Adapt to
Users
57
User modelling is always about guessing
58
User Model

• The user model is the systems representation of
  the users state of mind.
• The user model is actually a well-organized
  database, comprising information about the user.
• This is constructed in such a manner as to guide
  the systems inference engine.
• User model data are not static. They can be
  revised according to the current users actions
  as they are monitored by the system.

59
Classical User Model Overlay UM

• users knowledge subset of experts knowledge
• goal of tutoring to enlarge this subset.
• This model is particularly appropriate when the
  (teaching) material can be represented as a
  prerequisite hierarchy.

60
(No Transcript)
61
Adapt to what (else)?

• Knowledge about the subject domain (and possibly
  also knowledge about the system)
• Preferences
• Interests
• Learning or cognitive styles
• Background profession, language, prospect,
  capabilities
• Experience
• Navigation history

62
Adapt to what?

• Knowledge about the subject domain (possibly also
  knowledge about the system)
• The users knowledge is the basic driver behind
  the systems adaptation.
• Different users have different knowledge status
  about a specific subject.
• A single user can have variable knowledge status
  throughout his interaction with the system.
• The system must be able to recognize the users
  knowledge status, update his model and modify
  presentation and interaction accordingly.

63
Adapt to what?

• Preferences
• any explicitly entered aspect of the user that
  can be used for adaptation
• examples media preferences, cognitive style,
  etc.

64
Adapt to what?

• Interests
• what is the user after?
• what could be rewarding or not in the
  presentation?

65
Adapt to what?

• Learning or cognitive styles
• to be treated in the following section

66
Adapt to what?

• Background Experience
• background users experience outside the
  application
• experience users experience with the
  applications hyperspace

67
Adapt to what?

• Navigation history
• what has the user seen before coming here?

68
Index

• Definitions
• Why AH?
• Application areas
• What to adapt?
• Adapt to what?
• How to adapt - past?
• Obstacles AH
• New solutions