adaptive presentation for the web worasit choochaiwattana september 7, 2005
DESCRIPTION
3 References Adaptive Presentation for the Web by Andrea Bunt, Giuseppe Carenini and Cristina Conati Adaptive Presentation Supporting Focus and Context by Theophanis Tsandilas and m.c. Schraefel Personalised hypermedia presentation techniques for improving online customer relationships by Alfred Kobsa, Jurgen Koenemann and Wolfgang Pohl.TRANSCRIPT
![Page 1: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/1.jpg)
Adaptive Presentation for the Web
Worasit ChoochaiwattanaSeptember 7, 2005
![Page 2: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/2.jpg)
2
Agenda• Introduction• Techniques for content adaptation• Techniques for adaptive presentation• Q & A Session
![Page 3: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/3.jpg)
3
References• Adaptive Presentation for the Web by
Andrea Bunt, Giuseppe Carenini and Cristina Conati
• Adaptive Presentation Supporting Focus and Context by Theophanis Tsandilas and m.c. Schraefel
• Personalised hypermedia presentation techniques for improving online customer relationships by Alfred Kobsa, Jurgen Koenemann and Wolfgang Pohl.
![Page 4: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/4.jpg)
4
Introduction
Personalization Process in Hypermedia application
Acquisition Representation Production
![Page 5: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/5.jpg)
5
Techniques for content adaptation• Approaches Based on Page and
Fragment Variants• Approaches Based on Abstract
Information
![Page 6: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/6.jpg)
6
Approaches Based on Page and Fragment Variants
• Page-Variant approach
Adaptable Page + Model of
user/contextAdaptable Page + Model of
user/contextAdaptable
Page + Model of user/context
Adaptable Page + Model of
user/contextAdaptable Page + Model of
user/contextAdaptable Page + Model of
user/contextAdaptable Page + Model of
user/contextAdaptable Page
Model of user/context
Interaction Context
Adaptation Mechanism Presentation
![Page 7: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/7.jpg)
7
Approaches Based on Page and Fragment Variants
• Page-Variant approach– The approach does not scale up to
complex adaptation.– An unmanageable large number of variants
need to be written.
![Page 8: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/8.jpg)
8
Approaches Based on Page and Fragment Variants
• Fragment-Variant approach– The level of granularity of the adaptation is
increased.– The page presented to the user is
constructed by selecting and combining an appropriate set of fragments.
– Each fragments typically corresponds to a self-contained information element, such as text paragraphs or pictures.
![Page 9: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/9.jpg)
9
Approaches Based on Page and Fragment Variants
• Fragment-Variant approach– Two common strategies for fragment
variants are optional fragments and altering fragments.
– In optional fragments, a page is specified as a set of fragments, where each fragment is associated with a set of applicability conditions.
– At runtime, the page is generated by selecting only those fragments whose conditions are satisfied in the current interaction context.
![Page 10: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/10.jpg)
10
Approaches Based on Page and Fragment Variants
• Fragment-Variant approach– In altering fragments, a page is specified
as a set of constituents, and for each constituents there is a corresponding set of fragments.
– At runtime, the page is created by selecting for each constituent the fragment that is most appropriate in the current interaction context.
![Page 11: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/11.jpg)
11
Approaches Based on Page and Fragment Variants
• Fragment-Variant approach– The selection and assembly of a suitable
set of fragments may involve a substantial overhead at runtime.
– It may be sometimes difficult to combine the set of independently selected fragments into a coherent whole.
![Page 12: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/12.jpg)
12
Approaches Based on Page and Fragment Variants
• Fragment-Variant approach– Once a set of fragments and conditions on
their applicability have been written, a large number of pages can be automatically generated to cover a corresponding large number of situations.
![Page 13: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/13.jpg)
13
Approaches Based on Abstract Information
• Also called tailoring in NLG (Natural Language Generation)
• It requires an abstract representation of the domain from which the content is selected, as well as of the features of the interaction context to which the content is tailored.
• Several formalisms have been used– Knowledge Bases : HYLITE+– Bayesian Networks : NAG– Preference Models : GEA
![Page 14: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/14.jpg)
14
Approaches Based on Abstract Information
• The process of sophisticated content adaptation involves – Content Selection/Determination– Content Structuring
![Page 15: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/15.jpg)
15
Approaches Based on Abstract Information
• Content Selection/Determination– A subset of the domain knowledge is
identified.– In practice, most domain-independent
strategies for content selection compute a measure of relevance for each content element.
– Then, use this measure to select an appropriate subset of the available content.
![Page 16: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/16.jpg)
16
Approaches Based on Abstract Information
![Page 17: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/17.jpg)
17
Approaches Based on Abstract Information
• ILEX– The measure of relevance for content selection
combines a measure of structural relevance of knowledge element/fact with its intrinsic score.
– Structural relevance is computed starting form the focal entity by considering two basic heuristics
1. Information becomes less relevant the more distant it is from the focal object, in term of semantic links
2. Different semantic links maintain relevance to different degrees.
![Page 18: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/18.jpg)
18
Approaches Based on Abstract Information
• ILEX– As for the intrinsic score of a knowledge
element, it combines numerical estimates of three factors :• The potential interest of the information to the
current user• The importance of the information to the
system’s informational goals• The importance of the information to what
degree the user may already know this information
![Page 19: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/19.jpg)
19
Approaches Based on Abstract Information
• ILEX– The content selection strategy is to return
the n most relevant knowledge elements.– If the selection process based on
relevance cannot fine a sufficient number of knowledge elements, additional content selection routines are activated.
![Page 20: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/20.jpg)
20
Approaches Based on Abstract Information
![Page 21: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/21.jpg)
21
Approaches Based on Abstract Information
• RIA– Content selection is formalized as an
optimization problem.– The goal is to identify the most desirable subset
of data dimensions in the current interaction context.
– The desirability of each data dimension is computed as the linear combination of a large set of feature-based metrics that characterize how important the dimension is with respect to the interaction context.
– Most of these feature are labeled as content relevance features and include features of the data, features of user, as well as features relating the dimension to the user request and the interaction history.
![Page 22: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/22.jpg)
22
Approaches Based on Abstract Information
• RIA– Once all the available data dimensions
have been assigned their desirability, RIA’s content selection strategy returns the set of data dimensions such that their overall desirability is maximized and their cost is within given space and time allocated for the target presentation.
![Page 23: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/23.jpg)
23
Approaches Based on Abstract Information
• Content Structuring– This involves not only ordering and
grouping them, but also specifying what discourse relation must hold between the resulting groups.
– Schemas are the method of choice to accomplish all these tasks and are commonly implemented with task-decomposition planner.
![Page 24: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/24.jpg)
24
Evaluation of Content Adaptation Strategies
Evaluation ofContent Adaptation
Strategies
Human Judges
Human Designer
Task Efficacy
![Page 25: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/25.jpg)
25
Evaluation of Content Adaptation Strategies
• Human Judge – Requires a panel of judges to score both
the content selected by an adaptation strategy and non-adaptation strategy.
• Human Designer– A panel of experts select and rank what
they believe is the optimal content in that context.
– A distance metric will be applied to compare designer selection and adaptation technique selection.
![Page 26: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/26.jpg)
26
Evaluation of Content Adaptation Strategies
• The main limitation of them is that they require the specification of the interaction context to be simple enough that can be easily articulated to the experts.
• Task Efficacy– Allowing user to evaluate a content
adaptation technique by measuring on users’ behaviors, beliefs and attitudes in the context of task.
![Page 27: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/27.jpg)
27
Evaluation of Content Adaptation Strategies
• The main drawback is that task efficacy requires involving a larger number of users in the evaluation, making it an expensive and difficult-to-organize method.
• It is becoming a common choice in systems that perform sophisticated adaptation starting form abstract information.
![Page 28: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/28.jpg)
28
Techniques for Content Presentation
Techniques forContent
Presentation
Relevance-Based
Media Adaptation
Priority onFocus
Priority onContext
Stretchtext
Dimming Fragment
Scaling Fragment
![Page 29: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/29.jpg)
29
Relevance-Based Techniques• Two general dimension
– Maintaining Focus– Maintaining Context
• Context is more easily maintained if much of the original content is visible to the user.
• The more content is shown, the higher the chances of generating information overload and reducing attention to the most relevant information.
![Page 30: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/30.jpg)
30
Relevance-Based Techniques• The techniques can be grouped in two
main categories : Priority on Focus and Priority on Context.
![Page 31: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/31.jpg)
31
Priority on Focus• All of the techniques in this category
choose to maximize focus by– Showing only the most relevant content– Precluding access to the rest of the
context.• The two main drawbacks:
– The user has no way to recover from bad adaptation.
– They do not allow for user control.
![Page 32: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/32.jpg)
32
Priority on Context• This category includes the techniques
known as– Stretchtext– Dimming Fragments– Scaling Fragments (AKA Fisheye)
![Page 33: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/33.jpg)
33
Priority on Context• Stretchtext
– Preserve focus by hiding the less relevant content.
• Dimming Fragments– Deemphasize content by fading its color
• Scaling Fragments (AKA Fisheye)– Deemphasize content by reducing size
![Page 34: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/34.jpg)
34
Priority on Context
![Page 35: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/35.jpg)
35
Priority on Context
![Page 36: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/36.jpg)
36
Priority on Context
![Page 37: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/37.jpg)
37
Priority on Context• Tsandilas and Schraefel pointed out
that– Stretchtext performed better on larger
pages.– 4 of 6 subjects gave a higher score to
scaling because they felt it provides better information on the content of the deemphasized paragraphs.
• For more details, http://wwwis.win.tue.nl/ah2003/proceedings/ht-5/
![Page 38: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/38.jpg)
38
Priority on Context• Like scaling, dimming also preserves
distinctive structural elements of the available content, but it does not reduce page size.
![Page 39: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/39.jpg)
39
Technique for Media Adaptation• Adapting the medium (e.g. text, graphic,
spoken language)– Factors Relevant for Media Adaptation– Example of System– Media Adaptation Approach
• Rule-base approach• Optimization approach
![Page 40: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/40.jpg)
40
Factors Relevant for Media Adaptation
Factors Relevant for Media Adaptation
User-SpecificFeatures
InformationFeatures
MediaConstraints
Limitations ofTechnicalResources
PreferencesAbilitiesAccessibility
![Page 41: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/41.jpg)
41
Example of System• The CUMAPH adaptive hypermedia
environment adapts hypermedia documents according to user profile that describes the user’s cognitive abilities.
• The AVANTI system adapts the media according accessibility issues and resources issues.
• For more details, http://www.contrib.andrew.cmu.edu/~plb/UM97_workshop/Fink/Fink.html
![Page 42: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/42.jpg)
42
Media Adaptation Approach
MediaAdaptation
Rule-Based Optimization
![Page 43: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/43.jpg)
43
Rule-Based Approach• The vast majority of systems that
perform media adaptation are using rules that describe how to best convey the target information given subsets of the factors.
• Arens et al. describe a system that can adapt the media based on characteristics of the information to be conveyed, media constraints, the user’s interests and abilities, and the overall goals of the information presentation.
![Page 44: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/44.jpg)
44
Rule-Based Approach
Media allocation rulesPresentation Structure
Discourse Structure
Apply
Check
Layout SpecialistResult
![Page 45: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/45.jpg)
45
Optimization Approach• Formulate the media adaptation process as
an optimization problem.• CUMAPH (Cognitive User Modeling for
Adaptive Presentation of Hyper-Document) use two metrics : one for the media combination that best fits to the user profile; the other for combining multiple media.
• The system generates all possible combinations of media assignments to information item and picks the one whose sum of the two metrics is the highest.
![Page 46: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/46.jpg)
46
Optimization Approach• The advantage of the optimization
approach are– Not require a large set of rules.– Allow system to handle issues with
conflicting or interdependent factors without a large amount of communication among different system components.
– More easily extended– More easily to transferred to different
domains
![Page 47: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/47.jpg)
47
Q & A Session
![Page 48: Adaptive Presentation for the Web Worasit Choochaiwattana September 7, 2005](https://reader034.vdocument.in/reader034/viewer/2022051301/5a4d1b1b7f8b9ab0599936be/html5/thumbnails/48.jpg)
48
Thank you!!!