Adaptive hypermedia


Adaptive hypermedia uses hypermedia which is adaptive according to a [|user model]. In contrast to regular hypermedia, where all users are offered the same set of hyperlinks, adaptive hypermedia tailors what the user is offered based on a model of the user's goals, preferences and knowledge, thus providing links or content most appropriate to the current user.

Background

Adaptive hypermedia is used in educational hypermedia, on-line information and help systems, as well as institutional information systems. Adaptive educational hypermedia tailors what the learner sees to that learner's goals, abilities, needs, interests, and knowledge of the subject, by providing hyperlinks that are most relevant to the user in an effort to shape the user's cognitive load. The teaching tools "adapt" to the learner. On-line information systems provide reference access to information for users with a different knowledge level of the subject.
An adaptive hypermedia system should satisfy three criteria: it should be a hypertext or hypermedia system, it should have a user model and it should be able to adapt the hypermedia using the model.
A semantic distinction is made between adaptation, referring to system-driven changes for personalisation, and adaptability, referring to user-driven changes. One way of looking at this is that adaptation is automatic, whereas adaptability is not. From an epistemic point of view, adaptation can be described as analytic, a-priori, whereas adaptability is synthetic, a-posteriori. In other words, any adaptable system, as it "contains" a human, is by default "intelligent", whereas an adaptive system that presents "intelligence" is more surprising and thus more interesting.

Architecture

The system categories in which user modelling and adaptivity have been deployed by various researchers in the field share an underlying architecture. The conceptual structure for adaptive systems generally consists of interdependent components: a user model, a domain model and an interaction model.

User model

The user model is a representation of the knowledge and preferences which the system 'believes' a user possesses. It is a knowledge source which is separable by the system from the rest of its knowledge and contains explicit assumptions about the user. Knowledge for the user model can be acquired implicitly by making inferences about users from their interaction with the system, by carrying out some form of test, or from assigning users to generic user categories usually called 'stereotypes'. The student model consists of a personal profile, cognitive profile, and a student knowledge profile. Systems may adapt, depending on user features such as:
  • goals
  • knowledge
  • background
  • hyperspace experience
  • preferences.

    Domain model

The domain model defines the aspects of the application which can be adapted or which are otherwise required for the operation of the adaptive system. The domain model contains several concepts that stand as the backbone for the content of the system. Other terms which have been used for this concept include content model, application model, system model, device model and task model. It describes educational content such as information pages, examples, and problems. The simplest content model relates every content item to exactly one domain concept. More advanced content models use multi-concept indexing for each content item and sometimes use roles to express the nature of item-concept relationship.
A cognitively valid domain model should capture descriptions of the application at three levels, namely:
  • The task level which makes the user aware of the system purpose.
  • The logical level which describes how something works.
  • The physical level which describes how to do something.
Each content concept has a set of topics. Topics represent individual pieces of knowledge for each domain and the size of each topic varies in relation to the particular domain. Additionally, topics are linked to each other forming a semantic network. This network is the structure of the knowledge domain.

Interaction model

The interaction or adaptation model contains everything which is concerned with the relationships which exist between the representation of the users and the representation of the application. It displays information to the user based on his or her cognitive preferences. For instance, the module will divide a page's content into chunks with conditions set to only display to certain users or preparing two variants of a single concept page with a similar condition.
The two main aspects to the interaction model are capturing the appropriate raw data and representing the inferences, adaptations and evaluations which may occur.
Content-level and link-level adaptation are distinguished as two different classes of hypermedia adaptation; the first is termed adaptive presentation and the second, adaptive navigation support.

Adaptive presentation

The idea of various adaptive presentation techniques is to adapt the content of a page accessed by a particular user to current knowledge, goals, and other characteristics of the user.
For example, a qualified user can be provided with more detailed and deep information while a novice can receive additional explanations.
Adaptive text presentation is the most studied technology of hypermedia adaptation.
There are a number of different techniques for adaptive text presentation.

Adaptive navigation support

The idea of adaptive navigation support techniques is to help users to find their paths in hyperspace by adapting the way of presenting links to goals, knowledge, and other characteristics of an individual user.
This area of research is newer than adaptive presentation, a number of interesting techniques have been already suggested and implemented.
We distinguish four kinds of link presentation which are different from the point of what can be altered and adapted:
  • Local non-contextual links – This type includes all kinds of links on regular hypermedia pages which are independent from the content of the page.
  • Contextual links or "real hypertext" links – This type comprises "hotwords" in texts, "hot spots" in pictures, and other kinds of links which are embedded in the context of the page content and cannot be removed from it.
  • Links from index and content pages – An index or a content page can be considered as a special kind of page which contains only links.
  • Links on local maps and links on global hyperspace maps – Maps usually graphically represent a hyperspace or a local area of hyperspace as a network of nodes connected by arrows.

    Methods

Adaptation methods are defined as generalizations of existing adaptation techniques. Each method is based on a clear adaptation idea which can be presented at the conceptual level.

Content adaptation

  • additional explanations – hides parts of information about a particular concept which are not relevant to the user's level of knowledge about this concept,
  • prerequisite explanations – before presenting an explanation of a concept the system inserts explanations of all its prerequisite concepts which are not sufficiently known to the user,
  • comparative explanations – if a concept similar to the concept being presented is known, the user gets a comparative explanation which stress similarities and differences between the current concept and the related one,
  • explanation variants – assumes that showing or hiding some portion of the content is not always sufficient for the adaptation because different users may need essentially different information,
  • sorting – fragments of information about the concept are sorted from information which is most relevant to user's background and knowledge to information which is least relevant.

    Link adaptation

  • global guidance – the system suggests navigation paths on a global scale,
  • local guidance – the system suggests the next step to take, for instance through a "next" or "continue" button,
  • local orientation support – the system presents an overview of a part of the structure of the hyperspace,
  • global orientation support – the system presents an overview of the whole structure of the hyperspace,
  • managing personalized views in information spaces – each view may be a list of links to all pages or sub-parts of the whole hyperspace which are relevant for a particular working goal.

    Techniques

Adaptation techniques refer to methods of providing adaptation in existing AH systems.

Content adaptation

  • conditional text – with this technique, all possible information about a concept is divided into several chunks of texts. Each chunk is associated with a condition on the level of user knowledge represented in the user model. When presenting the information about the concept, the system presents only the chunks where the condition is true.
  • stretchtext – turns off and on different parts of the content according to the user knowledge level.
  • page variants – the most simple adaptive presentation technique. With this technique, a system keeps two or more variants of the same page with different presentations of the same content.
  • fragment variants – The system stores several variants of explanations for each concept and the user gets the page which includes variants corresponding to his or her knowledge about the concepts presented in the page
  • frame-based techniques – With this technique all the information about a particular concept is represented in form of a frame. Slots of a frame can contain several explanation variants of the concept, links to other frames, examples, etc. Special presentation rules are used to decide which slots should be presented to a particular user and in which order.