HCI Bibliography Home | HCI Conferences | UMAP Archive | Detailed Records | RefWorks | EndNote | Hide Abstracts
UMAP Tables of Contents: 00010203040506070809101112131415

Proceedings of AH 2006 Adaptive Hypermedia and Adaptive Web-based Systems 2006-06-21

Fullname:Proceedings of the 4th International Conference on Adaptive Hypermedia and Adaptive Web-Based Systems
Editors:Vincent P. Wade; Helen Ashman; Barry Smyth
Location:Dublin, Ireland
Dates:2006-Jun-21 to 2006-Jun-23
Series:Lecture Notes in Computer Science, 2006, Volume 4018
Standard No:ISBN: 978-3-540-34696-8 (Print) 978-3-540-34697-5 (Online); hcibib: UMAP06
Links:Online Proceedings
Summary:Adaptive Hypermedia and Adaptive Web Systems represent a critical and rapidly growing area of ICT research. Its focus on pioneering theories, techniques and innovative technologies to provide dynamic personalization, adaptation and contextualization of hypermedia resources and services has singled out the AH Conference series as the premier research event for adaptive Web systems. The conference combines state-of-the-art research investigations with industrial verification and evaluation to provide a unique event for researchers and practitioners alike. The conference series attracts researchers from the areas of knowledge engineering, artificial intelligence, Web engineering, Semantic Web, systems integration and security. In addition to these technology-and theoryoriented researchers, AH also attracts industrial and academic researchers in areas of key vertical markets such as interactive TV, e-learning, Web system, e-commerce and e-government.
  1. Keynote Speakers
  2. Full Papers
  3. Short Papers
  4. Posters
  5. Doctoral Consortium

Keynote Speakers

Knowledge-Driven Hyperlinks: Linking in the Wild BIBAFull-Text 1-10
  Sean Bechhofer; Yeliz Yesilada; Bernard Horan; Carole Goble
Since Ted Nelson coined the term "Hypertext", there has been extensive research on non-linear documents. With the enormous success of the Web, non-linear documents have become an important part of our daily life activities. However, the underlying hypertext infrastructure of the Web still lacks many features that Hypertext pioneers envisioned. With advances in the Semantic Web, we can address and improve some of these limitations. In this paper, we discuss some of these limitations, developments in Semantic Web technologies and present a system -- COHSE -- that dynamically links Web pages. We conclude with remarks on future directions for semantics-based linking.
Scrutable Adaptation: Because We Can and Must BIBAFull-Text 11-19
  Judy Kay
Beginning with the motivations for scrutability, this paper introduces PLUS, a vision of Pervasive Lifelong User-models that are Scrutable. The foundation for PLUS is the Accretion/Resolution representation for active user models that can drive adaptive hypermedia, with support for scrutability. The paper illustrates PLUS in terms of its existing, implemented elements as well as some examples of applications built upon this approach. The concluding section is a research agenda for essential elements of this PLUS vision.
Adapting NLP to Adaptive Hypermedia BIBAFull-Text 20
  Jon Oberlander
Natural Language Processing (NLP) techniques ought to be really useful for people building adaptive hypermedia (AH) systems. This talk explores the gap between theory and practice, illustrating it with examples of things that do (and don't work), and it suggests a way of closing the gap. The examples are mainly drawn from collaborative work I've been involved with over the last decade, on a series of AH systems using NLP: ILEX, SOLE, M-PIRO and Methodius. In theory, NLP sub-systems should help find, filter and format information for re-presentation in AH systems. So there ought to be lots of cross-fertilisation between NLP and AH. It is true that some projects have effectively brought them together; particularly on the formatting -- or information presentation -- side, natural language generation systems have allowed quite fine-grained personalisation of information to the language, interests and history of individual users. But in practice, NLP has been less useful to AH than one might have expected. Now, one reason for this is that the information to be presented has to come from somewhere, and NLP support for AH authors is not as good as it should be. Arguably, where NLP could really make a difference is on the finding and filtering side. State-of-the-art information extraction tools can increase author productivity, and help make fine-grained personalisation more practical.

Full Papers

Cross-Technique Mediation of User Models BIBAFull-Text 21-30
  Shlomo Berkovsky; Tsvi Kuflik; Francesco Ricci
Nowadays, personalization is considered a powerful approach for designing more precise and easy to use information search and recommendation tools. Since the quality of the personalization provided depends on the accuracy of the user models (UMs) managed by the system, it would be beneficial enriching these models through mediating partial UMs, built by other services. This paper proposes a cross-technique mediation of the UMs from collaborative to content-based services. According to this approach, content-based recommendations are built for the target users having no content-based user model, knowing his collaborative-based user model only. Experimental evaluation conducted in the domain of movies, shows that for small UMs, the personalization provided using the mediated content-based UMs outperforms the personalization provided using the original collaborative UMs.
Authoring Adaptive Learning Designs Using IMS LD BIBAFull-Text 31-40
  Adriana J. Berlanga; Francisco J. García; Jorge Carabias
Adaptive Educational Hypermedia Systems have the potential to deliver instruction tailored to the characteristics of each student. However, despite many years of research in the area, these systems have been used only in a few real learning situations. Reasons for this include their use of proprietary semantics in the definition of adaptivity and educational elements, and their lack of interoperation among courses and applications. We claim that an option to overcome these issues is to annotate adaptive rules, techniques, and learning elements using a common notational method, the IMS Learning Design (IMS LD). This paper presents a novel approach to define adaptive learning designs and, particularly, how adaptive hypermedia techniques and adaptive rules can be modelled by means of IMS LD.
Ways of Computing Diverse Collaborative Recommendations BIBAFull-Text 41-50
  Derek Bridge; John Paul Kelly
Conversational recommender systems adapt the sets of products they recommend in light of user feedback. Our contribution here is to devise and compare four different mechanisms for enhancing the diversity of the recommendations made by collaborative recommenders. Significantly, we increase diversity using collaborative data only. We find that measuring the distance between products using Hamming Distance is more effective than using Inverse Pearson Correlation.
Addictive Links: The Motivational Value of Adaptive Link Annotation in Educational Hypermedia BIBAFull-Text 51-60
  Peter Brusilovsky; Sergey Sosnovsky; Michael Yudelson
Adaptive link annotation is a popular adaptive navigation support technology. Empirical studies of adaptive annotation in the educational context have demonstrated that it can help students to acquire knowledge faster, improve learning outcome, reduce navigation overhead, and encourage non-sequential navigation. In this paper we present our study of a rather unknown effect of adaptive annotation, its ability to significantly increase student motivation to work with non-mandatory educational content. We explored this effect and confirmed its significance in the context of two different adaptive hypermedia systems. The paper presents and discusses the results of our work.
An Adaptive Personalized Recommendation Strategy Featuring Context Sensitive Content Adaptation BIBAFull-Text 61-70
  Zeina Chedrawy; Syed Sibte Raza Abidi
In this paper, we present a new approach that is a synergy of item-based Collaborative Filtering (CF) and Case Based Reasoning (CBR) for personalized recommendations. We present a two-phase strategy: in phase I, we developed a context-sensitive item-based CF method that leverages the original past recommendations of peers via ratings performed on various information items. In phase II, we further personalize the information items comprising multiple components using a CBR-based compositional adaptation technique to selectively collect the most relevant information components and combine them into one composite recommendation. In this way, our approach allows fine-grained information filtering by operating at the constituent elements of an information item as opposed to the entire information item. We show that our strategy improves the quality and relevancy of the recommendations in terms of its appropriateness to the user's needs and interests, and validated by statistical significance tests. We demonstrate the working of our strategy by recommending personalized music playlists.
An Empirical Study About Calibration of Adaptive Hints in Web-Based Adaptive Testing Environments BIBAFull-Text 71-80
  Ricardo Conejo; Eduardo Guzmán; José-Luis Pérez de-la Cruz; Eva Millán
In this paper we present a proposal for introducing hint adaptive selection in an adaptive web-based testing environment. To this end, a discussion of some aspects concerning the adaptive selection mechanism for hints is presented, which results in the statement of two axioms that such hints must fulfil. Then, an empirical study with real students is presented, whose goal is to evaluate a tentative bank of items with their associated hints to determine the usefulness of such hints for different knowledge levels and to calibrate both test items and hints.
Combining Adaptive Hypermedia Techniques and Ontology Reasoning to Produce Dynamic Personalized News Services BIBAFull-Text 81-90
  Owen Conlan; Ian O'Keeffe; Shane Tallon
Applying traditional Adaptive Hypermedia techniques to the personalization of news can pose a number of problems. The first main difficulty is the fact that news is inherently dynamic, thus producing an ever shifting pool from which content can be sourced. The second difficulty arises when trying to model a users interests and how they may be related to the available news items. This paper investigates the use of ontologies as a means of providing semantic bridges between available news items from RSS [1] news feeds and the interests of a user. Specifically, it investigates the combination of AH techniques with the ideas of loose and strict ontologies as the basis for personalization. This combination is highlighted through the design, development and evaluation of the Personalized News Service (PNS), which is based on the APeLS architecture [2].
Social Navigation Support in a Course Recommendation System BIBAFull-Text 91-100
  Rosta Farzan; Peter Brusilovsky
The volume of course-related information available to students is rapidly increasing. This abundance of information has created the need to help students find, organize, and use resources that match their individual goals, interests, and current knowledge. Our system, CourseAgent, presented in this paper, is an adaptive community-based hypermedia system, which provides social navigation course recommendations based on students' assessment of course relevance to their career goals. CourseAgent obtains students' explicit feedback as part of their natural interactivity with the system. This work presents our approach to eliciting explicit student feedback and then evaluates this approach.
Cooperating Search Communities BIBAFull-Text 101-110
  Jill Freyne; Barry Smyth
Collaborative Web Search (CWS) seeks to exploit the high degree of natural query repetition and result selection regularity that is prevalent among communities of searchers. CWS reuses the search experiences of community members, to promote results that have previously been judged relevant for queries. This facilitates a better response to the type of vague queries that are commonplace in Web search and allows a generic search engine to adapt to the preferences of communities of individuals. CWS contemplates a society of search communities, each with its own repository of experience. In this paper we describe and evaluate a new technique for leveraging the search experiences of related communities as sources of additional search knowledge.
Temporal Rules for Predicting User Navigation in the Mobile Web BIBAFull-Text 111-120
  Martin Halvey; Mark T. Keane; Barry Smyth
Numerous systems attempt to predict user navigation on the Internet through the use of past behavior, preferences and environmental factors. However many of these models have shortcomings, in that they do not take into account that browsers may have several different sets of preferences. Here we investigate time as an environmental factor in predicting user navigation in the Internet. We present methods for creating temporal rules that describe user navigation patterns. We also show the advantage of using these rules to predict user navigation and also illustrate the benefits of these models over traditional methods. An analysis is carried out on a sample of usage logs for Wireless Application Protocol (WAP) browsing, and the results of this analysis verify our theory.
The Value of QoE-Based Adaptation Approach in Educational Hypermedia: Empirical Evaluation BIBAFull-Text 121-130
  Cristina Hava Muntean; Jennifer McManis
This paper reports the results of a comparison-based empirical study on the applicability of the end-user Quality of Experience-based content adaptation mechanism in adaptive educational hypermedia. The focus of the paper will be the experiment itself: the initial settings, testing scenarios and the results. We will show that for low bit rate connections the QoE-based adaptation decreases study session time, information processing time per page and the number of re-visits to a page, it maintains similar learning outcomes while also improving the user quality of experience and satisfaction with the system. Finally we will comment on the results and interpret them.
GLAM: A Generic Layered Adaptation Model for Adaptive Hypermedia Systems BIBAFull-Text 131-140
  Cédric Jacquiot; Yolaine Bourda; Fabrice Popineau; Alexandre Delteil; Chantal Reynaud
This paper introduces GLAM, a system based on situation calculus and meta-rules, which is able to provide adaptation by means of selection of actions. It is primarily designed to provide adaptive navigation. The different levels of conception, related to different aspects of the available metadata, are split in different layers in GLAM, in order to ease the conception of the adaptation system as well as to increase the potential use of complex adaptation mechanisms. GLAM uses meta-rules to handle these layers.
Recomindation: New Functions for Augmented Memories BIBAFull-Text 141-150
  Carolin Plate; Nathalie Basselin; Alexander Kröner; Michael Schneider; Stephan Baldes
Advances in technological support for augmented personal memories make possible new ways of enhancing the process of product recommendation. Instead of simply analyzing information about a user's past behavior in order to generate recommendations, a recominder system can additionally supply various types of information from the user's augmented memory that allows the user to take a more active role in the search for suitable products. We illustrate the paradigm of recomindation with reference to a prototype implementation of the system SPECTER in a CD shopping scenario and the results of a study with 20 subjects, who found most of the recomindation functionality to constitute a useful enhancement of their shopping experience.
Automating Semantic Annotation to Enable Learning Content Adaptation BIBAFull-Text 151-160
  Jelena Jovanovic; Dragan Gasevic; Vladan Devedzic
This paper presents an approach to automatic annotation of learning objects' (LOs) content units that can be later assembled into new LOs personalized to the users' knowledge, preferences, and learning styles. Relying on a LO content structure ontology and some simple content-mining algorithms and heuristics, we manage to rather successfully determine the values of metadata elements aimed at annotating content units. Specifically, in this paper we present the specificities of generating metadata that describe the subject (based on a domain ontology) and the pedagogical role (based on an ontology of pedagogical roles) of a content unit. To test our approach we developed TANGRAM, an adaptive web-based educational environment for the domain of Intelligent Information system that enables on-the-fly assembly of personalized learning content out of existing content units.
A Scalable Solution for Adaptive Problem Sequencing and Its Evaluation BIBAKFull-Text 161-171
  Amruth Kumar
We propose an associative mechanism for adaptive generation of problems in intelligent tutors. Our evaluations of the tutors that use associative adaptation for problem sequencing show that 1) associative adaptation targets concepts less well understood by students; and 2) associative adaptation helps students learn with fewer practice problems. Apart from being domain-independent, the advantages of associative adaptation compared to other adaptive techniques are that it is easier to build and is scalable.
Keywords: Programming tutor; Adaptive Problem Sequencing; Evaluation
Interactions Between Stereotypes BIBAFull-Text 172-181
  Zoë Lock; Daniel Kudenko
Despite the fact that stereotyping has been used many times in recommender systems, little is known about why stereotyping is successful for some users but unsuccessful for others. To begin to address this issue, we conducted experiments in which stereotype-based user models were automatically constructed and the performance of overall user models and individual stereotypes observed. We have shown how concepts from data fusion, a previously unconnected field, can be applied to illustrate why the performance of stereotyping varies between users. Our study illustrates clearly that the interactions between stereotypes, in terms of their ratings of items, is a major factor in overall user model performance and that poor performance on the part of an individual stereotype need not directly cause poor overall user model performance.
Adaptation of Cross-Media Surveys to Heterogeneous Target Groups BIBAKFull-Text 182-191
  Alexander Lorz
Adaptive surveys provide an efficient method for customizing questionnaires to the particular requirements of a study and specific features of the respondent. Hypermedia can enhance the presentation of questionnaires and enables interactive feedback. As comparability of survey results is crucial, adaptation is constrained by the requirement of cognitive equivalence. The scenario of a survey-based early warning system for virtual enterprises supplies a context for the discussion of further requirements concerning structure, markup, and adaptation of surveys. An XML markup for adaptive surveys is proposed that is applied within a survey system for virtual enterprises.
Keywords: survey adaptation; adaptive questionnaire; XML
The Effect of Adapting Feedback Generality in ITS BIBAFull-Text 192-202
  Brent Martin; Antonija Mitrovic
Intelligent tutoring systems achieve much of their success by adapting to individual students. One potential avenue for personalization is feedback generality. This paper presents two evaluation studies that measure the effects of modifying feedback generality in a web-based Intelligent Tutoring System (ITS) based on the analysis of student models. The object of the experiments was to measure the effectiveness of varying feedback generality, and to determine whether this could be performed en masse or if personalization is needed. In an initial trial with a web-based ITS it appeared that it is feasible to use a mass approach to select appropriate concepts for generalizing feedback. A second study gave conflicting results and showed a relationship between generality and ability, highlighting the need for feedback to be personalized to individual students' needs.
An Authoring Tool for Building Both Mobile Adaptable Tests and Web-Based Adaptive or Classic Tests BIBAFull-Text 203-212
  Cristóbal Romero; Sebastián Ventura; Cesar Hervás; Paul De Bra
This paper describes Test Editor, an authoring tool for building both mobile adaptable tests and web-based adaptive or classic tests. This tool facilitates the development and maintenance of different types of XML-based multiple-choice tests for using in web-based education systems and wireless devices. We have integrated Test Editor into the AHA! system, but it can be used in other web-based systems as well. We have also created several test execution engines in Java language in order to be executed in different devices such as PC and mobile phones. In order to test them, we have carried out two experiments with students to determine the usefulness of adaptive tests and mobile tests.
ASHDM -- Model-Driven Adaptation and Meta-adaptation BIBAFull-Text 213-222
  Patricia Seefelder de Assis; Daniel Schwabe; Demetrius Arraes Nunes
In this work we propose a general purpose architecture for adaptation and meta-adaptation in hypermedia systems, using the Adaptive Semantic Hypermedia Design Model together with the Hypermedia Development Environment, extended to include adaptation. This architecture is model-driven and ontology-based, so data and model may be handled in the same way.
Visualizing Personal Relations in Online Communities BIBAFull-Text 223-233
  Andrew Webster; Julita Vassileva
A hard challenge facing developers of online communities is attaining a critical mass of members and subsequently sustaining their participation. We propose a new mechanism for motivating participation in interest-based online communities, which engages non-contributing members (lurkers) by modeling and visualizing the asymmetrical relations formed when reading, evaluating, or commenting other community members' contributions. The mechanism is based on ideas from open user modeling, a new concept of "community energy," with a mechanism of rating contributions and visualizing the rank of contributions in the community interface.
A Comparative Study of Compound Critique Generation in Conversational Recommender Systems BIBAKFull-Text 234-243
  Jiyong Zhang; Pearl Pu
Critiquing techniques provide an easy way for users to feedback their preferences over one or several attributes of the products in a conversational recommender system. While unit critiques only allow users to critique one attribute of the products each time, a well-generated set of compound critiques enables users to input their preferences on several attributes at the same time, and can potentially shorten the interaction cycles in finding the target products. As a result, the dynamic generation of compound critiques is a critical issue for designing the critique-based conversational recommender systems. In earlier research the Apriori algorithm has been adopted to generate compound critiques from the given data set. In this paper we propose an alternative approach for generating compound critiques based on the multi-attribute utility theory (MAUT). Our approach automatically updates the weights of the product attributes as the result of the interactive critiquing process. This modification of weights is then used to determine the compound critiques according to those products with the highest utility values. Our experiments show that the compound critiques generated by this approach are more efficient in helping users find their target products than those generated by the Apriori algorithm.
Keywords: conversational recommender system; critiquing; compound critique; multi-attribute utility theory; interaction cycle

Short Papers

Adapting Educational Hypermedia to Interaction Behaviors BIBAFull-Text 244-248
  Alessandro Assis; Michael Danchak; Linda Polhemus
This research investigated learner interaction with presentation, content and navigation adaptivity and its effect on time spent (efficiency) and performance (effectiveness) with three online tutorials. The tutorials were developed using a learning cycle to address the needs of all learners. Adaptivity was gradually introduced according to the learner interaction behavior with the cycle. Results from an analysis of variance (ANOVA) indicate that the amount of time spent was significantly reduced in the third and fully adaptive tutorial with comparable performance.
UbiquiTo-S: A Preliminary Step Toward Semantic Adaptive Web Services BIBAFull-Text 249-253
  Francesca Carmagnola; Federica Cena; Cristina Gena; Ilaria Torre
In this paper we describe an approach to design an adaptive system as a Semantic Web Service. We focus on how adaptive systems can provide adaptive services through web service technologies. In particular, we concentrate on adding semantic information to enrich the service discovery phase. We present a recommender system, UbiquiTO-S, which exploits the technology of Web Services (WS) and Semantic Web to allow software agents to discover its services and use its adaptive services.
Considering Additional Adaptation Concerns in the Design of Web Applications BIBAFull-Text 254-258
  Sven Casteleyn; Zoltán Fiala; Geert-Jan Houben; Kees van der Sluijs
The design of Web applications traditionally relies heavily on the navigation design. The Web as it evolves now brings additional design concerns, such as omni-presence, device-dependence, privacy, accessibility, localization etc. Many of these additional concerns are occurrences of user- or context-dependency, and are typically realized by transformations of the application (design) that embed adaptation in the navigation. In this paper we focus on how to extend an application with new functionality without having to redesign the entire application. If we can easily add functionality, we can separate additional design concerns and describe them independently. Using a component-based implementation we show how to extend a Web application to support additional design concerns at presentation generation level. Furthermore, we demonstrate how an Aspect-Oriented approach can support the high-level specification of these (additional) design concerns at a conceptual level.
Towards Measuring the Cost of Changing Adaptive Hypermedia Systems BIBAFull-Text 259-263
  Nathalie Colineau; Cécile Paris; Ross Wilkinson
As applications evolve over time, it becomes increasingly desirable to be able to adapt a system, enabling it to handle situations in different ways and to handle new situations. We refer to this as the flexibility and maintainability of a system. These features come at a cost. We argue here that they are an important aspect of evaluation, and that we need to measure these costs. To start getting a handle on how one might evaluate these aspects of a system (or of an approach), we turned to our own approach to building AH applications and designed a specific study to allow us to look at these issues.
Adaptive Patient Education Framework Featuring Personalized Cardiovascular Risk Management Interventions BIBAFull-Text 264-268
  Selena Davis; Syed Sibte Raza Abidi
The PULSE project objectives are to generate and evaluate a web-based personalized educational intervention for the management of cardiovascular risk. We present a web-based adaptive hypermedia system to create and deliver the personalized education material to the patient. The adaptive personalization framework is based on a patient profile created by combining an electronic patient data capture template, the Systematic COronary Risk Evaluation (SCORE) algorithm, and a Stage of behaviour Change determination model. The interventions are designed to address both medical and psychosocial aspects of risk management and, as such, we combine staged lifestyle modification materials and non-staged messages based on Canadian clinical guidelines to motivate personal risk management.
Using Contexts to Personalize Educational Topic Maps BIBAFull-Text 269-273
  Christo Dichev; Darina Dicheva
In this paper we discuss the support for personalization in TM4L -- an environment for building and using Topic Maps-based learning repositories. Our approach is based on the idea of using different views to access a learning collection depending on the context of its use. We propose an extension of the Topic Map model with contexts and discuss its implementation in TM4L aimed at supporting context-based personalization.
Combining Coherence and Adaptation in Discourse-Oriented Hypermedia Generation BIBAFull-Text 274-278
  Kateryna Falkovych; Federica Cena; Frank Nack
This paper provides a solution to discourse structure adaptation in the process of automatic hypermedia presentation generation. Existing approaches to discourse structure composition are based on the assumption that a user can comprehend relations between the elements in a discourse structure if the overall structure is semantically coherent. This assumption does not, so far, take into account specific user needs. In this paper we show that although discourse structure composition approaches significantly differ, a general model of the composition process can be derived. Within this general model we identify how adaptation can be applied. We formulate the problem of discourse adaptation with regard to the general model and present our proposed solution.
A Graph-Based Monitoring Tool for Adaptive Hypermedia Course Systems BIBAFull-Text 279-282
  Manuel Freire; Pilar Rodríguez
Adaptive hypermedia courses are difficult to debug, validate and maintain. Logfile analysis is partly to blame. We propose a graph-based approach to both real-time student monitoring and logfile analysis. Students are represented at their current locations in a dynamically created map of the course. Selected parts of student user models are visually exposed, and more detail is available on demand. Hierarchically clustered graphs, automatic layout and focus+context techniques are used to keep visual complexity at a manageable level. This component has been developed for an existing AH course system. However we believe that our approach can be readily extended to a wide selection of adaptive hypermedia course systems, filling in an important gap during course creation and maintenance.
Much to Know About History BIBAFull-Text 283-287
  Eelco Herder; Harald Weinreich; Hartmut Obendorf; Matthias Mayer
Users often revisit pages while browsing the Web, yet little is known on the character of these revisits. In this paper we present an analysis of various revisit activities, based on results from a long-term click-through study. We separate backtracking activities from recurrent behavior, discuss the impact of the use of multiple windows, and show that in particular infrequently reoccurring activities are poorly supported by current history support mechanisms. We conclude with a discussion on design implications for more personalized history support.
Learning Object Context for Adaptive Learning Design BIBAFull-Text 288-292
  Jelena Jovanovic; Dragan Gasevic; Colin Knight; Griff Richards
The paper presents an ontology-based framework for capturing and explicit representation of the actual context of use of a specific learning object (LO) in a specific learning design (LD). Learning context related data represented in such a manner provides a solid ground for personalization of both LOs and LDs. The core part of the proposed framework is a LO Context ontology, that leverages a range of other kinds of learning ontologies (e.g. user modeling ontology, domain ontology, LD ontology etc.) to capture the information about the real usage of a LO inside a LD. Additionally, we present the architecture of an adaptive educational system based on the suggested framework, in order to illustrate the benefits of our proposal for personalization of LD.
Personalised Navigation System with Multidimensional Linkbases BIBAFull-Text 293-297
  Panchit Longpradit; Christopher Bailey; Wendy Hall; Gary Wills
Adaptive hypermedia techniques provide users with personalisation of contents and links. Some of the criticisms of adaptive systems are that users do not always understand why the system is adapting the content and links [14], and that the adaptation process can lead to prolific or out of place linking. This paper introduces the concept of a multi-dimensional linkbase to describe a single linkbase containing links annotated with metadata that places them in several different contextual dimensions at once. We also allow users to have control over personalisation by enabling direct manipulation of the linkbase. We argue that this approach answer some of the criticisms of adaptive hypermedia.
Personalized Navigation in Open Information Space Represented by Ontology BIBAFull-Text 298-302
  Katarína Matusíková; Mária Bieliková
In this paper we deal with personalized navigation in an open information space in order to support effective orientation in increasing amount of information accessible through the web. We present a method for personalized navigation based on social navigation where information space is represented by an ontology. We discuss potential contributions of using the ontology representation for the navigation in open information spaces and for the navigational ability to deal with frequent change of the information contents.
A Unified Approach to Adaptive Hypermedia Personalisation and Adaptive Service Composition BIBAFull-Text 303-307
  Ian O'Keeffe; Owen Conlan; Vincent Wade
Adaptive Hypermedia is utilised in several domains, such as eLearning and professional training, where there is a growing movement towards the use of cognitively richer and more 'active' approaches to user engagement. In order to support this move, it is vital that adaptive personalisation systems, in these domains, are capable of integrating adaptively composed activities into adaptively personalised content compositions [1]. Through the integration of the approaches that are used in the automated composition of web services with those found in Adaptive Hypermedia, we believe that it will be possible to support a unified approach to the adaptation of content and services through the leveraging of the characteristics that are common to both adaptive application domains.
Can Adaptive Systems Participate in Their Design? Meta-adaptivity and the Evolution of Adaptive Behavior BIBAFull-Text 308-312
  Alexandros Paramythis
This paper discusses the opportunities arising from the employment of meta-adaptivity as a tool that can facilitate the design of adaptation. The discussion is structured around a specific example problem in the domain of adaptive course delivery systems. The paper builds upon this example to argue that meta-adaptivity is a viable solution to the "ground up" design of adaptive systems, and may be especially suited for cases where there is little empirically validated evidence to support design decisions.
A System for Adaptive Information Retrieval BIBAFull-Text 313-317
  Ioannis Psarras; Joemon Jose
In this paper, we describe the design and development of personal information assistant (PIA), a system aiming to meet individual needs of the searchers. The system's goal is to provide more up-to-date and relevant information to users with respect to their needs and interests. The main component of the system is a profile learner for capturing temporal user needs, based on implicit feedback gathering techniques. It monitors the system usage, the documents viewed and other user actions in order to infer users' changing needs.
Describing Adaptive Navigation Requirements of Web Applications BIBAFull-Text 318-322
  Gonzalo Rojas; Pedro Valderas; Vicente Pelechano
This work introduces a proposal to capture adaptive navigation characteristics of a Web Application in the Requirements Specification stage. Tasks that users must be able to achieve are identified and described, considering the navigational adaptations that are needed to fulfill them. By applying a given code generation strategy, it is possible to obtain fully operative prototypes of the adaptive web application from its requirements specification.
Learning Styles Adaptation Language for Adaptive Hypermedia BIBAFull-Text 323-327
  Natalia Stash; Alexandra Cristea; Paul De Bra
Typically, the behavior of adaptive systems is specified by a set of rules that are hidden somewhere in the system's implementation. These rules deal with instances of the domain model. Our purpose is to specify the adaptive response of the system at a higher level (to be applied and reused for different domains or adaptive applications) in an explicit form, called adaptation language. For this purpose we have chosen learning styles (LS) as an implementation field. We defined an XML-based adaptation language LAG-XLS for the AHA! system. In this paper we focus on the empirical evaluation of LAG-XLS.
Context-Based Navigational Support in Hypermedia BIBAFull-Text 328-332
  Sebastian Stober; Andreas Nürnberger
In this paper, we present the system "DAWN" (direction anticipation in web navigation) that helps users to navigate through the world wide web. Firstly, the purpose of such a system and the approach taken are motivated. We then point out relations to other approaches, describe the system and outline the underlying prediction model. Evaluation on real world data gave promising results.
Contextual Media Integration and Recommendation for Mobile Medical Diagnosis BIBAFull-Text 333-337
  David Wilson; Eoin McLoughlin; Dympna O'Sullivan; Michela Bertolotto
Hospitals everywhere are taking advantage of the flexibility and speed of wireless computing to improve the quality and reduce the cost of healthcare. Caregivers equipped with portable computers now have levels of interaction at the bedside not possible with paper charts and can leverage accurate real-time patient information at the point of care to diagnose and treat patients with greater speed and efficiency. We present a mobile medical application that integrates heterogenous medical media (e.g. textual patient case descriptions, relevant medical imagery, physician dictations and endoscopies) into encapsulated patient profiles. This paper provides an overview and initial evaluation of the MEDIC mobile healthcare recommender system that facilitates decision support for expert diagnosis.


User Modelling: An Empirical Study for Affect Perception Through Keyboard and Speech in a Bi-modal User Interface BIBAFull-Text 338-341
  Efthymios Alepis; Maria Virvou
This paper presents and discusses an empirical study that has been conducted among different kinds of computer users. The aim of the empirical study was to find out how computer users react when they face situations which generate emotions while they interact with a computer. The study has focused on two modes of human-computer interaction namely input from the keyboard and the microphone. The results of the study have been analyzed in terms of characteristics of users that have taken part (age, educational level, computer knowledge, etc.). These results were used to create a user modeling component that monitors users silently and records their actions (in the two modes of interaction) which are then interpreted in terms of their feelings. This user modeling component can be incorporated in any application that provides adaptive interaction to users based on affect perception.
The AHES Taxonomy: Extending Adaptive Hypermedia to Software Components BIBAFull-Text 342-345
  Frank Hanisch; Meike Muckenhaupt; Franz Kurfess; Wolfgang Straßer
Hypermedia has matured to XML-based specifications and Java/Flash software componentry. In this contribution we extend known adaptation methods and techniques to software programs and classify them by component type. We consider adaptation of internal multimedia structures, graphics elements, interactions, and included algorithms. Methods are illustrated with a prototype system that implements matching, component-based adaptation techniques. It is available for free and includes an XML authoring schema, an adaptation layer for third-party Java applets, and a server-side adaptation engine.
Web-Based Recommendation Strategy in a Cadastre Information System BIBAFull-Text 346-349
  Dariusz Król; Michaó Szymanski; Bogdan Trawinski
Web-based recommendation strategy implemented in a cadastre information system is presented in the paper. This method forms the list of page profiles recommended to a given user. The idea of page recommendation uses the concept of a page profile for system pages containing forms with search criteria. The calculation of rank values for page profiles is based on the usage frequency and the significance weights of profile elements determined by users.
Topic-Centered Adaptive Curriculum for E-Learning BIBAFull-Text 350-353
  Yanyan Li; Ronghuai Huang
This paper proposes an approach to dynamically compose an adaptive curriculum for e-learning based on a topic-centered resource space. By exploiting the semantic relationships that characterize learning objects (LOs) and learner profile, the approach dynamically selects, sequences, and links learning resources into a coherent, individualized curriculum to address learners' focused learning needs. We developed an active learning system with semantic support for learners to access and navigate through learning resources in an efficient and personalized manner, while providing facilities for instructors to manipulate the structured learning resources via a convenient visual interface.
Semantic-Based Thematic Search for Personalized E-Learning BIBAFull-Text 354-357
  Yanyan Li; Ronghuai Huang
This paper describes one solution to the problem of how to collect, organize, and select Web learning resources into a coherent, focused organization for instruction to address learners' immediate and focused learning needs. By exploiting the semantic relationships that characterize learning resources and learner profile, the proposed semantic-based thematic approach supports both semantic querying and conceptual navigation of learning resources pertaining to specific topics. A system has been developed and deployed within an academic setting, enabling learners to organize, search, and share the learning resources in a flexible and personalized manner.
Adaptation in Adaptable Personal Information Environment BIBAFull-Text 358-361
  Thanyalak Maneewatthana; Gary Wills; Wendy Hall
In order to support knowledge workers during their tasks of searching, locating and manipulating information, a system that provides information suitable for a particular user's needs, and that is also able to facilitate annotation, sharing and reuse information is essential. This paper presents Adaptable Personal Information Environment (a-PIE); a service-oriented framework using Open Hypermedia and Semantic Web technologies to provide an adaptable web-based system. a-PIE models the information structures (data and links) and context as Fundamental Open Hypermedia Model (FOHM) structures which are manipulated by using the Auld Linky contextual link service. a-PIE provides an information environment that enables users to search an information space based on ontologically defined domain concepts. The users can add and annotate interesting data or parts of information structures into their information space, leaving the original published data or information structures unchanged. a-PIE facilitates the shareability and reusability of knowledge according to users' requirements.
Towards Formalising Adaptive Behaviour Within the Scope of E-Learning BIBAFull-Text 362-365
  Felix Mödritscher
As there are a lot of approaches and projects within the area of adaptive e-learning, several theoretical models have been developed in the last 15 years. Against this background, the AdeLE team implemented a first prototype on basis of informal descriptions given by literature research as well as concrete circumstances of the research project. Nevertheless, a theoretical model fulfilling certain requirements for our approach is still missing. This paper points out possibilities and limitations of existing models in the scope of the AdeLE project. Further, the author's own attempt towards formalising adaptive behaviour in e-learning environments is denoted.
Informing Context to Support Adaptive Services BIBAFull-Text 366-369
  Alexander O'Connor; Vincent Wade
A common trend in modern applications is the move towards more mobile, adaptive, customisable software. The evolution of software from static, invariant tools for narrow portions of a task to adaptive, open interaction frameworks is embodied in the use of a variety of technologies for creating a reconfigurable application. Perhaps the two most important techniques are Adaptive architectures and Ubiquitious Computing. However, many techniques employed merging these two technologies to form the vision of a truly ubiquitous, adaptive environment have so far failed to take full account of the expressive quality of both context and adaptivity. This paper presents a new, semantic interopration-based approach to creating context-informed adaptive applications that make maximum use of the rich content that can be found in both technologies.
eDAADe: An Adaptive Recommendation System for Comparison and Analysis of Architectural Precedents BIBAFull-Text 370-373
  Shu-Feng Pan; Ji-Hyun Lee
We built a Web-based adaptive recommendation system for students to select and suggest architectural cases when they analyze "Case Study" work within the architectural design studio course, which includes deep comparisons and analyses for meaningful architectural precedents. We applied hybrid recommendation mechanism, which is combining both content-based filtering and collaborative filtering in our suggested model. It not only retains the advantages of a content-based and collaborative filtering approach, but also improves the disadvantages found in both. We expect that the approach would be helpful for students to find relevant precedents more efficient and more precise with their preferences.
On the Dynamic Adaptation of Computer Assisted Assessment of Free-Text Answers BIBAFull-Text 374-377
  Diana Pérez-Marín; Enrique Alfonseca; Pilar Rodríguez
To our knowledge, every free-text Computer Assisted Assessment (CAA) system automatically scores the students and gives feedback to them according to their responses, but, none of them include yet personalization options. The free-text CAA system Atenea [1] had simple adaptation possibilities by keeping static student profiles [2]. In this paper, we present a new adaptive version called Willow. It is based on Atenea and adds the possibility of dynamically choosing the questions to be asked according to their difficulty level, the students' profile and previous answers. Both Atenea and Willow have been tested with 32 students that manifested their satisfaction after using them. The results stimulate us to continue exploiting the possibilities of incorporating dynamic adaptation to free-text CAA.
An Adaptive Hypermedia System Using a Constraint Satisfaction Approach for Information Personalization BIBAFull-Text 378-388
  Syed Sibte Raza Abidi; Yan Zeng
Adaptive hypermedia systems offer the functionality to personalize the information experience as per a user-model. In this paper we present a novel content adaptation approach that views information personalization as a constraint satisfaction problem. Information personalization is achieved by satisfying two constraints: (1) relevancy constraints to determine the relevance of a document to a user and (2) co-existence constraints to suggest complementing documents that either provide reinforcing viewpoints or contrasting viewpoints, as per the user's request. Our information personalization framework involves: (a) an automatic constraint acquisition method, based on association rule mining on a corpus of documents; and (b) a hybrid of constraint satisfaction and optimization methods to derive an optimal solution -- i.e. personalized information. We apply this framework to filter news items using the Reuters-21578 dataset.
My Compiler Really Understands Me: An Adaptive Programming Language Tutor BIBAFull-Text 389-392
  Kate Taylor; Simon Moore
We describe an intelligent interactive online tutor for computer languages. The tutor uses an ontology of programming language terms together with a language-specific ontology. These ontologies are embedded in web pages structured at different levels of student expertise to provide a web front end that can be re-assembled in many different ways to suit a particular student's attempt to compile a particular program. This dynamic reassembly copes well with the initial learning curve for a language as well as revision a few months later. We argue that such a dynamic solution is more appropriate in this case than user profiling as a student's capabilities are not the same for all parts of the language to be learnt or from one session to the next. Our system gives the student control over the learning process by the use of question answering techniques on the same ontology. Our system tracks what the user is doing in the programming exercises to understand what they are trying to write. Early trials with a real student audience have produced positive results and feedback for more research.

Doctoral Consortium

Adaptive Learning for Very Young Learners BIBAFull-Text 393-397
  J. Enrique Agudo; Héctor Sánchez; Mercedes Rico
The use of Information and Communication Technologies (ICTs) is spreading inside the classrooms at all educational levels. As this integration has extended to young learners (3 to 5 years), the authorities have recommended their use so that children can acquire knowledge and dexterities they will use all their lives. Keeping in mind that it is at this age when very young learners acquire abilities and basic dexterities at their own pace, the more personalized the better. From all the premises above, we can claim that whereas other computer assisted language learning systems do not account for differences in children's cognitive development when designing computerized applications, the introduction of AHS (Adaptive Hypermedia Systems) is aimed at adapting and personalizing content to children's needs and abilities.
A Collaborative Constraint-Based Adaptive System for Learning Object-Oriented Analysis and Design Using UML BIBAFull-Text 398-403
  Nilufar Baghaei
This paper presents COLLECT-UML, a constraint-based ITS that teaches object-oriented (OO) design using Unified Modeling Language (UML). We have developed a single-user version that supports students in learning UML class diagrams. The system was evaluated in a real classroom, and the results show that student performance increases significantly. We present our experiences in extending the system to provide support for collaboration and describe the architecture, interface and support for collaboration in the new, multi-user system.
Decentralized Mediation of User Models for a Better Personalization BIBAFull-Text 404-408
  Shlomo Berkovsky
The growth of available personalization services and the heterogeneity in content and representation of therein exploited User Models (UMs), raise a need for a mechanism allowing to aggregate partial UMs generated by other services. Such a mechanism will allow reuse of partial UMs in multiple personalization services that may need it. This paper discusses the details of a decentralized mediator for cross-domain and cross-technique translation and aggregation of partial UMs. The mediator facilitates enriching UMs managed by personalization services and improving the quality of the provided personalization.
From Interoperable User Models to Interoperable User Modeling BIBAFull-Text 409-413
  Francesca Carmagnola; Federica Cena
Currently, there is an increasing demand user-adaptive systems for various purposes in many different domains. The development of such systems requires computational efforts which is often challenging and off-putting. The main contribution of our work is the idea to go one step further from sharing user model data (interoperable user models) towards the exchange of user model reasoning strategies (interoperable user modeling). In this paper we discuss, exemplified in a concrete scenario, how Semantic Web techniques may be applied to the field of the Adaptive Systems in order to have a more effective and reliable user model interoperability, considering both the perspectives of User Modeling Servers and Web Servers.
Assessment of Motivation in Online Learning Environments BIBAFull-Text 414-418
  Mihaela Cocea
This research outline refers to the assessment of motivation in online learning environments. It includes a presentation of previous approaches, most of them based on Keller's ARCS model, and argues for an approach based on Social Cognitive Learning Theory, in particular building on self-efficacy and self-regulation concepts. The research plan includes two steps: first, detect the learners in danger of dropping-out based on their interaction with the system; second, create a model of the learner's motivation (including self-efficacy, self-regulation, goal orientation, attribution and perceived task characteristics) upon which intervention can be done.
User-System-Experience Model for User Centered Design in Computer Games BIBAFull-Text 419-424
  Ben Cowley; Darryl Charles; Michaela Black; Ray Hickey
This paper details the central ideas to date, from a PhD entitled 'Player Profiling for Adaptive Artificial Intelligence in Computer and Video Games'. Computer and videogames differ from other web and productivity software in that games are much more highly interactive and immersive experiences. Whereas usability and user modelling for other software may be based on productivity alone, games require an additional factor that takes account of the quality of the user experience in playing a game. In order to describe that experience we describe a model of User, System and Experience (USE) in which the primary construct for evaluation of a player's experience will be the Experience Fluctuation Model (EFM), taken from Flow theory. We illustrate with a straightforward example how this system may be automated in real-time within a commercial game.
Adaptive Support for Cross-Language Text Retrieval BIBAFull-Text 425-429
  Ernesto William De Luca; Andreas Nürnberger
In this paper we discuss ideas for adaptive support of cross-language text retrieval. In order to enable users to access multilingual information, different problems have to be solved: disambiguating and translating the query words, as well as categorizing and presenting the results appropriately. After giving a brief introduction to cross-language text retrieval, word sense disambiguation and document categorization, actual achievements of the research project are described and future work is discussed. We focus especially on the problem of browsing and navigation of the different word senses in a source and target languages.
Some Ideas for a Collaborative Search of the Optimal Learning Path BIBAFull-Text 430-434
  Sergio Gutiérrez Santos; Abelardo Pardo; Carlos Delgado Kloos
One of the challenges of adaptive hypermedia educational (AHE) systems is that of adapting the sequencing of learning units presented to the student. One approach is to model the set of possible sequencings with a graph, but the process of designing and maintaining the graph may be tedious and error-prone. This paper presents some ideas to overcome this, inspired by swarm intelligence techniques. Problems that may arise, as well as possible solutions, are presented.
Interception of User's Interests on the Web BIBAFull-Text 435-439
  Michal Barla
Current adaptive systems acquire information about users mainly by simple tracking of resources, a user has requested and by asking users to supply the needed information. In this paper, we discuss user modeling based on observing a user's interaction with the system. We propose to collect usage data on the server side as well as on the client side. Collected data are then processed into knowledge about user's intentions and preferences. This processing relies on a set of heuristics, which help to interpret the usage patterns found in the collected data.
Intervention Strategies to Increase Self-efficacy and Self-regulation in Adaptive On-Line Learning BIBAFull-Text 440-444
  Teresa Hurley
This research outline refers to the validation of interventional strategies to increase the learner's motivation and self-efficacy in an on-line learning environment. Previous work in this area is mainly based on Keller's ARCS model of instructional design and this study argues for an approach based on Bandura's Social Cognitive Theory -- especially the aspects of self-efficacy and self-regulation. The research plan envisages two phases: The first phase will extract rules for interventional strategy selection from expert teachers. The second phase aims to validate these rules by providing to the learner the selected strategy and observing the resulting behavior.
Dynamic Content Discovery, Harvesting and Delivery, from Open Corpus Sources, for Adaptive Systems BIBAFull-Text 445-451
  Séamus Lawless; Vincent Wade
Personalised elearning is being heralded as one of the grand challenges of next generation learning systems, in particular, its ability to support greater effectiveness, efficiency and student empowerment. However, a key problem with such systems is their reliance on bespoke content developed for, and only used by, these systems. The challenge for adaptive systems in scalably supporting personalised elearning is its ability to source, harvest and deliver open corpus content to adaptive content services and personalised elearning systems. This paper examines the issues involved in implementing such an adaptive content service. The paper seeks to explore the accurate extraction of content requirements from the adaptive system, the sourcing and identification of suitable learning content, the harvesting and customisation of the content for delivery to adaptive elearning systems.
Personalised Multimodal Interfaces for Mobile Geographic Information Systems BIBAFull-Text 452-456
  Eoin Mac Aoidh
HCI in GIS is complicated by information overload and inappropriately designed user interfaces considering the task at hand. Implicit user profiling makes it possible to personalise both the data displayed by the GIS, and the interface used to display this data. The advance of mobile computing in recent years has put a great demand on mobile GIS to be made more efficient and user-friendly, as GIS are best experienced in the field. While operating in the field, it is quite conceivable that one's hands would be otherwise occupied, thus the advancement of a multimodal system is imperative for field operation. This doctoral consortium paper addresses the personalisation of the HCI with such a mobile GIS.
A Model for Personalized Learning Through IDTV BIBAFull-Text 457-461
  Marta Rey-López; Ana Fernández-Vilas; Rebeca P. Díaz-Redondo
Interactive Digital TV (IDTV) opens new learning possibilities where new forms of education are needed. In this paper we explain a new conception of t-learning experiences where TV programs and learning contents are combined. In order for its creation to be possible we will use Adaptive Hypermedia techniques and Semantic Reasoning to design an Intelligent Tutoring System (ITS) whose tasks consist in selecting, combining and personalizing the contents to construct these learning experiences.
Performance Enhancement for Open Corpus Adaptive Hypermedia Systems BIBAFull-Text 462-466
  Lejla Rovcanin; Cristina Hava Muntean; Gabriel-Miro Muntean
Adaptive Hypermedia Systems adjust the content to best suit users' personal characteristics, but rarely consider delivery performance. Performance issues are even more significant in distributed architectures such as that of an Open Corpus Adaptive Educational Hypermedia System (OAEHS). This paper introduces a Performance Oriented Adaptation Agent (POAA) that enhances OAEHS by taking into consideration not only user personal characteristics but also network delivery conditions in the content selection process. The usage of POAA is expected to bring significant delivery performance improvements in terms of learner satisfaction and learning outcome.
Personalized Navigation in the Semantic Web BIBAFull-Text 467-471
  Michal Tvarozek
Effective navigation and information retrieval is difficult and time consuming due to the increasing size of hyperspace. The introduction of the semantic web allows us to enhance traditional search methods with semantic search capabilities that take advantage of machine readable semantic information ideally stored in an ontology. Nevertheless issues concerning the user-friendly construction of search queries and a simple yet effective presentation of search results must still be addressed. The proposed approach takes advantage of adaptive hypermedia in an enhanced faceted browser capable of dynamically adapting the set of available facets with additional support for data retrieval from an ontology and adaptive annotation of search results.