© Copyright 2006 Texas Digital Library. All Rights Reserved.
Vol 7, No 1 (2006)
Articles
End-User Quality of Experience Oriented Adaptive E-learning System
In the context of new devices and with a variety of network technologies that allow access to the Internet, the providers of e-learning materials have to ensure that the users have a positive experience using their e-learning systems and they are happy to re-use them. Adaptive Hypermedia research aims to provide personalised educational material that ensures a positive learning experience for the end-users. However, user experience is dependent not only on the content served to them, but also on the user perceived performance of the e-learning system. This leads to a new dimension of individual differences between Web users: the end-user Quality of Experience (QoE). We have proposed a solution for Adaptive Hypermedia Systems (AHS) that provides satisfactory end-user QoE through the use of a new QoE layer. This layer attempts to take into account multiple factors affecting QoE in relation to the delivery of a wide range of Web components such as text, images, video, audio. The effectiveness of our QoE layer has been tested in comparison to a standard educational AHS and the results of these tests are presented in this paper. Different educational-based evaluation techniques such as learner achievement analysis, learning performance assessment, usability survey and correlation analysis between individual student performance and judgment on system usability were applied in order to fully assess the performance of the proposed QoE layer. Results of the tests showed that the use of the QoE layer brought significant improvments in terms of user learning performance, system usability and user satisfaction with the personalised e-learning system while not affecting the user learning achievement.
View full text: HTML
Conflict Management in Multi-model Adaptive Hypermedia
New adaptive hypermedia systems are employing multiple independent models in order to better guide their adaptation mechanisms by considering relevant factors in addition to user characteristics. This approach promises an enhanced system responsiveness and functionality. However, it also entails the possibility of conflicts as different models can suggest adapting the document in contradicting ways. Finding mechanisms capable of automatically managing these conflicts is a key issue in the development of this new generation of adaptive hypermedia systems. This work provides an approach that delivers a context-sensitive solution to this issue within the field of adaptive spatial hypermedia. The paper reports how this approach was instantiated and included in the WARP system. Details about its architecture, adaptation process and key features are discussed in order to inform and enable the design of the next generation of multi-model adaptive systems.
View full text: PDF
Multimodal Content Adaptations for Heterogeneous Devices
We present Multiface, a multimodal dialog system that allows users to interact using different devices such as desktop computers, PDAs, and mobile phones. Users can request information and will receive multimodal responses, where the presented content and its modality are customized to individual and the device they are using. In addition, the system will attempt to assess the user's understanding and adapt its future responses accordingly. Multiface uses a plan-based approach to produce adaptive content and modalities from an annotated document and models of the user and device.
View full text: PDF
A Framework for Automated Evaluation of Hypertext Search Interfaces
An evaluation framework and simulator of an interactive information retrieval system (SIIIRS) is introduced. SIIIRS is designed to allow researchers to conduct many exploratory studies that can help to narrow the focus of future human subject studies by showing which differences in information exploration style and functionality are likely to produce significant differences in future human subject studies. An experiment was carried out to demonstrate how SIIIRS could be used to predict performance when using different search strategies in a dynamic hypertext environment. The analysis of both the performance and behavioural measures obtained in the experiment showed significant differences in how the different agents (search strategies) performed when using different combinations of query difficulty, newness, and query tail size (as defined in the research reported in this paper). Overall, the agents differed in terms of their behaviours compared to one another and in terms of their interaction with the simulator parameter of newness and the dynamic hypertext control parameter of query tail size. The analysis of the behavioural measures showed the same pattern as found in the performance measures, with query tail size (an indicator of how easy it is to modify the topic during the search) having a strong influence on performance. The results of this study are discussed in terms of their implications for future automated evaluation of hypertext search interfaces.
View full text: PDF