Work on developing team models for use in adaptive systems generally and intelligent tutoring systems more specifically has largely focused on the task skills or learning efficacy of teams working on short-term projects in highly-controlled virtual environments. In this work, we report on the development of a balanced team model that takes into account task skills, teamwork behaviours and team workflow that has been empirically evaluated via an uncontrolled real-world long-term pilot study of student software engineering teams. We also discuss the use of the the J4.8 machine learning algorithm with our team model in the construction of a team performance prediction system.

Work on developing team models for use in adaptive systems generally and intelligent tutoring systems more specifically has largely focused on the task skills or learning efficacy of teams working on short-term projects in highly-controlled virtual environments. In this work, we report on the development of a balanced team model that takes into account task skills, teamwork behaviours and team workflow that has been empirically evaluated via an uncontrolled real-world long-term pilot study of student software engineering teams. We also discuss the use of the the J4.8 machine learning algorithm with our team model in the construction of a team performance prediction system.

End-users tend to lose their way in the maze of information within hypertext. Much work done to address the "lost in hyperspace" problem is reactive, that is, doing remedial work to correct the deficiencies within hypertexts because they are (or were) poorly designed and built. What if solutions are sought to avoid the problem? What if we do things well from the start? This thesis reviews the "lost in hyperspace" problem, and suggests a framework to understand the design and usability issues. These issues cannot be seen as purely psychological or purely computing, they are multi-disciplinary. The proactive, multi-disciplinary approach undertaken in this thesis is drawn from current technologies in sub-disciplines of hypertext, human-computer interaction, cognitive psychology and software engineering, and they include investigations into: " good design principles and guidelines for the building of hypertexts in the first place; " task analysis and user modelling techniques for end-users' tasks to be carefully defined; " effective hypertext structures to ensure usability of hypertexts; and " designer tools to create hypertexts with a reduced tendency for the "lost in hyperspace" problem to arise. To demonstrate these ideas, this thesis presents HyperAT, a hypertext research authoring tool, developed to help designers build usable web documents on the World Wide Web. The World Wide Web is chosen as a hypertext example since it is the most widely used and largest hypertext system ever. The approach taken in HyperAT is novel: multi-disciplinary approaches are integrated and implemented with a practical authoring tool. Evaluation of HyperAT indicates that it does address the "lost in hyperspace" problem, particularly for the World Wide Web by: (i) helping designers manage the complexity of the design and validation processes; and (ii) helping hypertext end-users navigate hypertexts produced by HyperAT without getting "lost".

Yes / Intercultural competence is an essential 21st Century skill. A key issue for developers of cross-cultural training simulators is the need to provide relevant learning experience adapted to the learner’s abilities. This paper presents a dialogic approach for a quick assessment of the depth of a learner's current intercultural awareness as part of the EU ImREAL project. To support the dialogue, Linked Data is seen as a rich knowledge base for a diverse range of resources on cultural aspects. This paper investigates how semantic technologies could be used to: (a) extract a pool of concrete culturally-relevant facts from DBpedia that can be linked to various cultural groups and to the learner, (b) model a learner's knowledge on a selected set of cultural themes and (c) provide a novel, adaptive and user-friendly, user modelling dialogue for cultural awareness. The usability and usefulness of the approach is evaluated by CrowdFlower and Expert Inspection.

No / We investigate how to provide personalized nudges to aid a user’s exploration of linked data in a way leading to expanding her domain knowledge. This requires a model of the user’s familiarity with domain concepts. The paper examines an approach to detect user domain familiarity by exploiting anchoring concepts which provide a backbone for probing interactions over the linked data graph. Basic level concepts studied in Cognitive Science are adopted. A user study examines how such concepts can be utilized to deal with the cold start user modelling problem, which informs a probing algorithm.

Profiling is an approach to put a label or a set of labels on a subject, considering the characteristics of this subject. The New Oxford American Dictionary defines profiling as: “recording and analysis of a person’s psychological and behavioral characteristics, so as to assess or predict his/her capabilities in a certain sphere or to assist in identifying a particular subgroup of people”. This research extends this definition towards things demonstrating that many methods used for profiling of people may be applied for a different type of subjects, namely things. The goal of this research concerns proposing methods for discovery of profiles of users and things with application of Data Science methods. The profiles are utilized in vertical and 2 horizontal scenarios and concern such domains as smart grid and telecommunication (vertical scenarios), and support provided both for the needs of authorization and personalization (horizontal usage).:The thesis consists of eight chapters including an introduction and a summary. First chapter describes motivation for work that was carried out for the last 8 years together with discussion on its importance both for research and business practice. The motivation for this work is much broader and emerges also from business importance of profiling and personalization. The introduction summarizes major research directions, provides research questions, goals and supplementary objectives addressed in the thesis. Research methodology is also described, showing impact of methodological aspects on the work undertaken. Chapter 2 provides introduction to the notion of profiling. The definition of profiling is introduced. Here, also a relation of a user profile to an identity is discussed. The papers included in this chapter show not only how broadly a profile may be understood, but also how a profile may be constructed considering different data sources. Profiling methods are introduced in Chapter 3. This chapter refers to the notion of a profile developed using the BFI-44 personality test and outcomes of a survey related to color preferences of people with a specific personality. Moreover, insights into profiling of relations between people are provided, with a focus on quality of a relation emerging from contacts between two entities. Chapters from 4 to 7 present different scenarios that benefit from application of profiling methods. Chapter 4 starts with introducing the notion of a public utility company that in the thesis is discussed using examples from smart grid and telecommunication. Then, in chapter 4 follows a description of research results regarding profiling for the smart grid, focusing on a profile of a prosumer and forecasting demand and production of the electric energy in the smart grid what can be influenced e.g. by weather or profiles of appliances. Chapter 5 presents application of profiling techniques in the field of telecommunication. Besides presenting profiling methods based on telecommunication data, in particular on Call Detail Records, also scenarios and issues related to privacy and trust are addressed. Chapter 6 and Chapter 7 target at horizontal applications of profiling that may be of benefit for multiple domains. Chapter 6 concerns profiling for authentication using un-typical data sources such as Call Detail Records or data from a mobile phone describing the user behavior. Besides proposing methods, also limitations are discussed. In addition, as a side research effect a methodology for evaluation of authentication methods is proposed. Chapter 7 concerns personalization and consists of two diverse parts. Firstly, behavioral profiles to change interface and behavior of the system are proposed and applied. The performance of solutions personalizing content either locally or on the server is studied. Then, profiles of customers of shopping centers are created based on paths identified using Call Detail Records. The analysis demonstrates that the data that is collected for one purpose, may significantly influence other business scenarios. Chapter 8 summarizes the research results achieved by the author of this document. It presents contribution over state of the art as well as some insights into the future work planned.

In digital environments, colour is used for many purposes: for example, to encode information in charts, signify missing field information on websites, and identify active windows and menus. However, many people have inherited, acquired, or situationally-induced Colour Vision Deficiency (CVD), and therefore have difficulties differentiating many colours. Recolouring tools have been developed that modify interface colours to make them more differentiable for people with CVD, but these tools rely on models of colour differentiation that do not represent the majority of people with CVD. As a result, existing recolouring tools do not help most people with CVD. To solve this problem, I developed Situation-Specific Modelling (SSM), and applied it to colour differentiation to develop the Individualized model of Colour Differentiation (ICD). SSM utilizes an in-situ calibration procedure to measure a particular user’s abilities within a particular situation, and a modelling component to extend the calibration measurements into a full representation of the user’s abilities. ICD applies in-situ calibration to measuring a user’s unique colour differentiation abilities, and contains a modelling component that is capable of representing the colour differentiation abilities of almost any individual with CVD. This dissertation presents four versions of the ICD and one application of the ICD to recolouring. First, I describe the development and evaluation of a feasibility implementation of the ICD that tests the viability of the SSM approach. Second, I present revised calibration and modelling components of the ICD that reduce the calibration time from 32 minutes to two minutes. Next, I describe the third and fourth ICD versions that improve the applicability of the ICD to recolouring tools by reducing the colour differentiation prediction time and increasing the power of each prediction. Finally, I present a new recolouring tool (ICDRecolour) that uses the ICD model to steer the recolouring process. In a comparative evaluation, ICDRecolour achieved 90% colour matching accuracy for participants – 20% better than existing recolouring tools – for a wide range of CVDs. By modelling the colour differentiation abilities of a particular user in a particular environment, the ICD enables the extension of recolouring tools to helping most people with CVD, thereby reducing the difficulties that people with CVD experience when using colour in digital environments.

This study attempted to combine the benefits of multimedia learning, adaptive interfaces, and learning style theory by constructing a novel e-learning environment. The environment was designed to accommodate individual learning styles while students progressed through a computer programming course. Despite the benefits of individualised instruction and a growing worldwide e-learning market, there is a paucity of guidance on how to effectively accommodate learning styles in an online environment. Several existing learning-style adaptive environments base their behaviour on an initial assessment of the learner's profile, which is then assumed to remain stable. Consequently, these environments rarely offer the learner choices between different versions of content. However, these choices could cater for flexible learning styles, promote cognitive flexibility, and increase learner control. The first research question underlying the project asked how learning styles could be accommodated in an adaptive e-learning environment. The second question asked whether a dynamically adaptive environment that provides the learner with a choice of media experiences is more beneficial than a statically adapted environment. To answer these questions, an adaptive e-learning environment named iWeaver was created and experimentally evaluated. iWeaver was based on an introductory course in Java programming and offered learning content as style-specific media experiences, assisted by additional learning tools. These experiences and tools were based on the perceptual and information processing dimension of an adapted version of the Dunn and Dunn learning styles model. An experimental evaluation of iWeaver was conducted with 63 multimedia students. The analysis investigated the effect of having a choice of multiple media experiences (compared to having just one static media experience) on learning gain, enjoyment, perceived progress, and motivation. In addition to these quantitative measurements, learners provided qualitative feedback at the end of each lesson. Data from 27 participants were sufficiently complete to be analysed. For the data analysis, participants were divided into two groups of high and low interest in programming and Java, then into two groups of high and low experience with computers and the Internet. Both group comparisons revealed statistically significant differences for the effect of choice. Having a choice of media experiences proved beneficial for learners with low experience but detrimental for learners with high experience or interest. These findings suggest that the effect of choice appears to be strongly influenced by the learner's background. It is hypothesised that encouraging a more active learner role in educational systems would expand the positive influence of choice to a wider range of learners. The study has contributed some weight to the argument that for certain groups of learners, it is more beneficial to view learning style as a flexible, rather than a stable construct. As a practical implication, it seems advisable to collect data on prior experience, interest, and the initial learning style distribution of the target audience before developing environments comparable to iWeaver. [See http://www.adaptive-learning.net/research/media.htm for media files associated with this thesis.]

<p>This thesis presents a set of concepts and a general design approach for designing Mixed Reality environments based on the idea that the physical (real) world and the virtual (digital) world are equally important and share many properties. Focus is on the design of a technology infrastructure intended to relieve people from some of the extra efforts currently needed when performing activities that make heavy use of both worlds. An important part of the proposed infrastructure is the idea of creating Physical-Virtual Artefacts, objects manifested in the physical and the virtual world at the same time.</p><p>The presented work challenges the common view of Human-Computer Interaction as a research discipline mainly dealing with the design of “user interfaces” by proposing an alternative or complementary view, a physical-virtual design perspective, abstracting away the user interface, leaving only physical and virtual objects. There are at least three motives for adopting such a design perspective: 1) people well acquainted with specific (physical and virtual) environments are typically more concerned with the manipulation of (physical and virtual) objects than the user interface through which they are accessed. 2) Such a design stance facilitates the conceptualisation of objects that bridge the gap between the physical and the virtual world. 3) Many physical and virtual objects are manifested in both worlds already today. The existing conceptual link between these physical and virtual objects has only to be complemented with causal relations in order to reduce the costs in crossing the border between the physical and the virtual world.</p><p>A range of concepts are defined and discussed at length in order to frame the design space, including<i> physical-virtual environment gap, physical-virtual activity, physical-virtual artefact, </i>and<i> physical-virtual environment</i>.</p><p>Two conceptual models of physical-virtual space are presented as a result of adopting the physical-virtual design perspective: for the analysis of object logistics in the context of physical-virtual activities, and for describing structural properties of physical-virtual space respectively. A prototype system offering some degree of physical-virtual infrastructure is also presented.</p>

This thesis presents a set of concepts and a general design approach for designing Mixed Reality environments based on the idea that the physical (real) world and the virtual (digital) world are equally important and share many properties. Focus is on the design of a technology infrastructure intended to relieve people from some of the extra efforts currently needed when performing activities that make heavy use of both worlds. An important part of the proposed infrastructure is the idea of creating Physical-Virtual Artefacts, objects manifested in the physical and the virtual world at the same time. The presented work challenges the common view of Human-Computer Interaction as a research discipline mainly dealing with the design of “user interfaces” by proposing an alternative or complementary view, a physical-virtual design perspective, abstracting away the user interface, leaving only physical and virtual objects. There are at least three motives for adopting such a design perspective: 1) people well acquainted with specific (physical and virtual) environments are typically more concerned with the manipulation of (physical and virtual) objects than the user interface through which they are accessed. 2) Such a design stance facilitates the conceptualisation of objects that bridge the gap between the physical and the virtual world. 3) Many physical and virtual objects are manifested in both worlds already today. The existing conceptual link between these physical and virtual objects has only to be complemented with causal relations in order to reduce the costs in crossing the border between the physical and the virtual world. A range of concepts are defined and discussed at length in order to frame the design space, including physical-virtual environment gap, physical-virtual activity, physical-virtual artefact, and physical-virtual environment. Two conceptual models of physical-virtual space are presented as a result of adopting the physical-virtual design perspective: for the analysis of object logistics in the context of physical-virtual activities, and for describing structural properties of physical-virtual space respectively. A prototype system offering some degree of physical-virtual infrastructure is also presented.