Alexandros Paramythis

Layered evaluation of interactive adaptive systems: framework and formative methods

The evaluation of interactive adaptive systems has long been acknowledged to be a complicated and demanding endeavour. Some promising approaches in the recent past have attempted tackling the problem of evaluating adaptivity by “decomposing” and evaluating it in a “piece-wise” manner. Separating the evaluation of different aspects can help to identify problems in the adaptation process. This paper presents a framework that can be used to guide the “layered” evaluation of adaptive systems, and a set of formative methods that have been tailored or specially developed for the evaluation of adaptivity. The proposed framework unifies previous approaches in the literature and has already been used, in various guises, in recent research work. The presented methods are related to the layers in the framework and the stages in the development lifecycle of interactive systems. The paper also discusses practical issues surrounding the employment of the above, and provides a brief overview of complementary and alternative approaches in the literature.

Activity sequence modelling and dynamic clustering for personalized e-learning

Monitoring and interpreting sequential learner activities has the potential to improve adaptivity and personalization within educational environments. We present an approach based on the modeling of learners’ problem solving activity sequences, and on the use of the models in targeted, and ultimately automated clustering, resulting in the discovery of new, semantically meaningful information about the learners. The approach is applicable at different levels: to detect pre-defined, well-established problem solving styles, to identify problem solving styles by analyzing learner behaviour along known learning dimensions, and to semi-automatically discover learning dimensions and concrete problem solving patterns. This article describes the approach itself, demonstrates the feasibility of applying it on real-world data, and discusses aspects of the approach that can be adjusted for different learning contexts. Finally, we address the incorporation of the proposed approach in the adaptation cycle, from data acquisition to adaptive system interventions in the interaction process.

A decomposition model for the layered evaluation of interactive adaptive systems

A promising approach towards evaluating adaptive systems is to decompose the adaptation process and evaluate the system in a “piece-wise” manner. This paper presents a decomposition model that integrates two previous proposals. The main “stages” identified are: (a) collection of input data, (b) interpretation of the collected data, (c) modeling of the current state of the “world”, (d) deciding upon adaptation, and (e) applying adaptation.

User satisfaction with home telecare based on broadband communication

Home telecare services based on broadband communication were established in five locations in Europe. Two different types of telecare unit were developed: one based on a PC or set-top box containing a videoconferencing codec and another on off-the-shelf videoconferencing units. The participants in the project were 13 medical staff, 135 patients and 88 people informally caring for the patients. Questionnaires were used to evaluate user satisfaction with eight telecare services. Almost all participants rated the usability of the system as good or excellent. A total of 105 telecare sessions were scored by the medical staff. Overall, the quality of audio and video communication was judged satisfactory. For the patients and carers, the perceived quality of communication was also satisfactory and did not vary significantly between sites. The medical staff were reasonably satisfied with how the service supported them in their work. Except for the item about being able to support patients in a critical situation, medical staff agreed that an improved quality of health services was offered through telecare. All participants agreed that personal information was treated confidentially and that there was little risk in using the telecare services. The medical staff trusted the assessments they could make remotely while using the telecare system. Although the findings cannot be generalized due to the small number of telecare sessions and the relatively short duration of the experiment, the results encourage further research.

Web Accessibility through Adaptation

This paper presents the eAccessibilityEngine tool, which employs adaptation techniques to automatically render web pages accessible by users with different types of disabilities. Specifically, the eAccessibilityEngine is capable of automatically transforming web pages to attain AAA-level conformance to the W3C WAI Web Content Accessibility Guidelines and to “Section 508” of the US Rehabilitation Act. The proposed tool is intended for use as a web-based service and can be applied to any existing web site.

Towards improved support for adaptive collaboration scripting in IMS LD

The IMS Learning Design specification is acknowledged as the most promising option available presently for the implementation of collaboration scripts in e-learning. Nevertheless, it has been criticized for a number of shortcomings, and, specifically for its lack of support for constructs that would enable comprehensive adaptive support to be effected over the collaborative learning process. In this paper we propose concrete extensions to the specification, which build upon prior work and address a wide range of problems and omissions. The most important modifications introduced include: explicit support for groups, and run-time member assignment; addition of a run-time model; introduction of concrete artefacts; introduction of an event-handling model; and, a modified sequencing and script organization model.

Using thematic ontologies for user- and group-based adaptive personalization in web searching

This paper presents Prospector, an adaptive meta-search layer, which performs personalized re-ordering of search results. Prospector combines elements from two approaches to adaptive search support: (a) collaborative web searching; and, (b) personalized searching using semantic metadata. The paper focuses on the way semantic metadata and the users’ search behavior are utilized for user- and group- modeling, as well as on how these models are used to re-rank results returned for individual queries. The paper also outlines past evaluation activities related to Prospector, and discusses potential applications of the approach for the adaptive retrieval of multimedia documents.

Towards Adaptive Learning Support on the Basis of Behavioural Patterns in Learning Activity Sequences

Monitoring and interpreting sequential user activities contributes to enhanced, more fine-grained user models in e-learning systems. We present in this paper different behavioural patterns from the domain of problem-solving that can be determined by targeted, ultimately automated clustering. For the identification of these patterns, we apply a new approach - based on the modeling of activity sequences - to real-world learning activity sequence data, monitored via an Intelligent Tutoring System. This paper describes the identified behavioural patterns, explains the process used for their detection, and compares the patterns to related ones in earlier literature. It further discusses implications of the patterns themselves, and of the employed approach, on adaptively supporting individual and group-based collaborative learning.

Closing the Circle: IMS LD Extensions for Advanced Adaptive Collaboration Support

This paper, the third in a series, completes the presentation of a proposed set of modifications and extensions to the IMS Learning Design specification with the goal of enabling better support for adaptivity in collaborative learning settings. The extensions presented here target advanced adaptation features that build upon previous work and include: adapting control flows, controlling adaptations on a meta-level, human involvement in adaptation decisions, “transactional” action processing, loops and branches for controlling action execution, declaration of re-usable action sequences and complex expressions, and mechanisms for exception handling.

Collaboration Contexts, Services, Events and Actions: Four Steps Closer to Adaptive Collaboration Support in IMS LD

The IMS Learning Design specification, a widely known language for modelling collaboration scripts, has been criticized for a number of shortcomings and general lack of support for comprehensive adaptation features. We propose concrete extensions to the specification, aiming to alleviate deficiencies by specifically addressing (group) collaboration contexts, flexible service specification, fine-grained event handling and a wide range of adaptive interventions to support learners.