Search

Any physical space can be augmented with digital information, associated to various locations or artefacts contained in it. In this paper, an abstract architecture is presented, supporting interaction with mobile context aware applications in public digitally augmented spaces. We focus on how this architecture supports personalization of interaction and adaptation. The main goal of the architecture is to allow users to benefit of a uniform and personalized experience across different contexts and spaces. Among the concerns are: to support high interoperability and flexibility and to address issues of privacy and user control. The framework has been tested in typical augmented spaces: a library and a museum. The paper concludes with a set of examples of use of the defined framework that cover typical situations for intra-space and across spaces usage. [ABSTRACT FROM AUTHOR]

This paper presents the main findings, and lessons learned, from introducing a synchronous peer collaboration activity in a distance learning computer science course. Synergo, a software that supports such an approach, was used in this activity. The organizational, technical, and academic challenges of introducing this activity in the course are discussed. After analyzing the students' interaction and their opinions, and evaluating the final results, it was found that this activity was received positively by the group of students concerned, who engaged in peer tutoring and used this as an opportunity to break the isolation of the distance learning setting and to forge links with each other. [ABSTRACT FROM AUTHOR]

During the last decade an increased interest has been observed on computer-supported collaborative problem solving. This relatively new area of research requires new methodological approaches of interaction and problem solving analysis. Usually analysis of collaborative problem solving situations is done through discourse analysis or interaction analysis, where in the center of attention are the actors involved (students, tutors etc.). An alternative framework, called “Object-oriented Collaboration Analysis Framework (OCAF)” is presented here, according to which the objects of the collaboratively developed solution become the center of attention and are studied as entities that carry their own history. This approach produces a reversed view of the process, according to which the solution is made of structural components that are ‘owned’ by actors who have contributed in various degrees to their development. OCAF provides both qualitative and quantitative measures of collaboration. It is shown that this framework can be applied effectively both in synchronous computer supported collaborative environments of distance groups and in face-to-face collaborative activities. [Copyright &y& Elsevier]

Management of urban atmospheric pollution necessitates advanced modeling and information processing techniques. The design of the prototype system DNEMO, which is based on a distributed adaptive problem-solving approach is the focus of the research reported in this paper. Issues covered in the paper relate to the distributed nature of this environmental problem, handling noise and uncertainty in monitoring data, achieving graceful degradation of performance and system robustness, and adaptation of system performance to long-term evolution of the monitored phenomena. The research reported can be applicable to a broad class of environmental monitoring applications, since the problems addressed are common to many environmental problems. [ABSTRACT FROM AUTHOR]

Mixed-reality environments introduce innovative human-computer interaction paradigms assisted by enhanced visual content presentation which require from end-users to perform excessive cognitive tasks related to visual attention, search, processing, and comprehension. In such visually enriched interaction realms, individual differences in perception and visual information processing might affect users’ behaviour and immersion, given that such effects are known to exist in conventional computer environments, like desktop or mobile. In an attempt to shed light on whether, how, and why such effects persist within mixed-reality contexts, we conducted a between-subjects eye-tracking study (N=73) in which users interacted within either a conventional or a mixed-reality technological context, and adopted an accredited cognitive style theory to interpret the derived results. Analysis of results yielded that mixed-reality interaction realms amplified the effects of human cognitive style towards game-specific interaction behaviour and visual behaviour. Findings further support the added value of incorporating human cognitive factors in both design and run-time, aiming to provide adaptive and personalised features to end-users within mixed-reality interaction contexts. Such practical implications are also discussed in this paper. [ABSTRACT FROM AUTHOR]

Information overload in MOOC discussion forums is a major problem that hinders the effectiveness of learner facilitation by the course staff. To address this issue, supervised classification models have been studied and developed in order to assist course facilitators in detecting forum discussions that seek for their intervention. A key issue studied by the literature refers to the transferability of these models to domains other than the domain in which they were initially trained. Typically these models employ domain-dependent features, and therefore they fail to transfer to other subject matters. In this study, we propose and evaluate an alternative way of building supervised models in this context, by using the semantic similarities of the forum transcripts with the dynamically created corpora from the MOOC environment as training features. Specifically, in this study, we analyze the case of two MOOCs, in which the models that we built are classifying forum discussions into three categories, course logistics, content-related and no action required. Furthermore, we evaluate the transferability of the derived models and interpret which features can be effectively transferred to other unseen courses. The findings of this study reveal the main benefits and trade-offs of the proposed approach and provide MOOC developers with insights about the main issues that inhibit the transferability of these models. [ABSTRACT FROM AUTHOR]

This paper presents and discusses a survey of existing tools to support design and evaluation of websites, with special emphasis on improving the information navigation process. The amount of information of today's websites, the continuous evolution of the medium and the heterogeneity of typical users' profiles, make the website design task particularly hard. The presented tools are mainly based on recent models of Web usage behavior, and involve various natural language and semantic similarity modeling methods. Validation studies of the presented tools have shown that they can support effectively various phases of the website design lifecycle including information structuring, hyperlink evaluation and assessment of alternative designs. In this paper, existing techniques are discussed, the aspects of Web design that (should and) could be better supported are identified and suggestions are made on extensions of existing approaches to better support the usability evaluation process. [ABSTRACT FROM AUTHOR]

Following information scent has been established as a metaphor to describe a user's behaviour while navigating an information space by successively selecting hyperlinks. This metaphor suggests that users assess the profitability of following a particular hyperlink based on its perceived semantic association with their goal. The purpose of this paper is to study how information scent, this important attribute of hypermedia navigability, influences concurrently four aspects of users' behaviour while exploring a website: (1) distribution of attention; (2) confidence in choice of link; (3) efficiency; and (4) effectiveness. It was found that in webpages with high scent, users were significantly more focused, confident of their choices, efficient and effective compared to webpages with ambiguous scent. The findings of the study are discussed in comparison with results obtained from a previously conducted analysis using InfoScent Evaluator (ISEtool), a tool that has been proposed to facilitate scent evaluation of websites. This comparison provided support for the effectiveness of ISEtool in indicating potential scent-related navigability problems. We argue that such a tool-based approach can facilitate hypermedia design by reducing the resources and expertise required, and by providing the necessary flexibility for practitioners. [ABSTRACT FROM AUTHOR]

Abstract: Structuring of the content is an important step in web site design, affecting greatly navigability and the overall user experience. Automated support of this task is the object of this paper. AutoCardSorter, a computational tool that supports clustering of the web pages of a site, is introduced. The proposed tool-based methodology uses semantic similarity measures, such as latent semantic analysis, and hierarchical clustering algorithms, in order to suggest suitable information navigation schemes. In the paper, after introducing AutoCardSorter design and functionality, three independent studies are discussed. The studies, that were conducted in order to validate the proposal, compared the proposed method with the established card-sorting approach, in different domains. It was found that substantial gain in effectiveness was achieved without expense in the quality of results, therefore, reducing the required time and human resources. [Copyright &y& Elsevier]

Classification problems with uneven class distributions present several difficulties during the training as well as during the evaluation process of classifiers. A classification problem with such characteristics has resulted from a data mining project where the objective was to predict customer insolvency. Using the data set from the customer insolvency problem, we study several alternative methodologies, which have been reported to better suit the specific characteristics of this type of problem. Three different but equally important directions are examined: (a) the performance measures that should be used for problems in this domain; (b) the class distributions that should be used for the training data sets; and (c) the classification algorithms to be used. The final evaluation of the resulting classifiers is based on a study of the economic impact of classification results. This study concludes to a framework that provides the “best” classifiers, identifies the performance measures that should be used as the decision criterion, and suggests the “best” class distribution based on the value of the relative gain from correct classification in the positive class. This framework has been applied in the customer insolvency problem, but it is claimed that it can be applied to many similar problems with uneven class distributions that almost always require a multi-objective evaluation process. [ABSTRACT FROM AUTHOR]

Graphical password composition is an important part of graphical user authentication which affects the strength of the chosen password. Considering that graphical authentication is associated with visual search, perception, and information retrieval, in this paper we report on an eye-tracking study (N = 109) that aimed to investigate the effects of users' cognitive styles toward the strength of the created passwords and shed light into whether and how the visual strategy of the users during graphical password composition is associated with the passwords' strength. For doing so, we adopted Witkin's Field Dependence-Independence theory, which underpins individual differences in visual information and cognitive processing, as graphical password composition tasks are associated with visual search. The analysis revealed that users with different cognitive processing characteristics followed different patterns of visual behavior during password composition which affected the strength of the created passwords. The findings underpin the need of considering human-cognitive characteristics as a design factor in graphical password schemes. The paper concludes by discussing implications for improving recognition-based graphical passwords through adaptation and personalization techniques based on individual cognitive characteristics. [ABSTRACT FROM AUTHOR]

A correction to this paper has been published: https://doi.org/10.1007/s00521-021-05904-z [ABSTRACT FROM AUTHOR]

When people interact with digital artefacts they perceive theirpragmaticandhedonic qualities. In the case of interacting with mobile devices and applications, users seek utility as they try to satisfy certain needs, but at the same time they have certain feelings and emotions when, for example, they feel attached to their personal phone and/or trust its brand. Due to this strong relation between users and mobile devices a significant problem occurs when researchers want to evaluate the user experience of a mobile application in laboratory settings: the selection of an appropriate mobile device. Towards this end, this paper aims to unveil the effect of perceivedhedonic qualityof a mobile device on the user experience evaluation results of an application. Our results show that the perceivedhedonic qualityof a mobile device significantly affected the perceivedpragmaticquality of the application, but not thehedonicone. [ABSTRACT FROM PUBLISHER]

During the last years, development of open learning environments that support effectively their users has been a challenge for the research community of educational technologies. The open interactive nature of these environments results in users experiencing difficulties in coping with the plethora of available functions, especially during their initial efforts to use the system. In addition, -from the tutors' perspective- the problem solving strategies of the students are often particularly difficult to identify. In this paper, we argue that such problems could be tackled using machine learning techniques such as Bayesian Networks. We show how we can take advantage of log files obtained during field studies to build an adaptive help system providing the most useful support to the student, according to the state of interaction. On the other hand, we attempt to support the tutor, by automating the process of diagnosing students' problem solving strategies using Bayesian Networks. The presented approaches are discussed through examples of two prototypes that have been developed and corresponding evaluation studies. These studies have shown that the proposed approach can effectively support the tasks of students and tutors in such open learning environments. [ABSTRACT FROM AUTHOR]

This paper examines the effect of heterogeneous resources, available to students, during computer-supported collaborative problem solving. A study of collaborative modeling has been conducted in the frame of an authentic educational activity in a secondary school. The students involved were provided with sets of primitive resources of varying degrees of heterogeneity to be used during synchronous computer-mediated modeling activities. Analysis of students'' peer interaction and of the produced solutions revealed that, contrary to our expectations, the group with heterogeneous resources produced solutions of similar quality to those of the reference group, although they were more active, they exchanged more messages, they were involved in deeper discussions and collaborated more for building the constituent parts of the solution. [Copyright &y& Elsevier]

Feature selection is a process of determining the most relevant features of a given problem in order to improve the generalization and the performance of a relevant classification or regression algorithm. This paper focuses on the exploitation of a genetic algorithm following a wrapping iterative approach used to extract an optimal feature subset of a large database containing pollutant concentration measurements. The feature subset is fed to a machine learning algorithm in order to predict the daily maximum concentration of two air pollutants. The encoding problem of the complexity of representation of the features in the genomes is tackled. Results of the experimentation on a specific dataset of an air quality forecasting problem are presented, as well as some proposed alterations on the standard genetic algorithm that guided the process to a mature convergence and gave good solutions for this problem. A modified version of the initial algorithm is presented as well, implemented for the purpose of being compared on an equal basis with other feature selection methods. Two such methods of the filtering type, CFS and ReliefF, are being compared with. The comparative results suggest that the wrapping type technique described in this paper is significantly better in the specific problem at hand, but this conclusion is limited to the machine learning algorithm that the technique uses at its core in the feature selection phase. [ABSTRACT FROM AUTHOR]