AI personalisation has emerged as a powerful tool to boost consumer satisfaction in digital experiences. Satisfaction is a multifaceted concept, encompassing the fulfilment of needs and wants and resulting in a positive emotional and cognitive state. This study describes how AI personalisation can strengthen overall satisfaction by aligning AI recommendations along with both observable needs and deeper emotional and social desires. To investigate this, a qualitative research approach was employed, utilising semi-structured interviews to gather empirical data. This method ensured comprehensive coverage of the topic while allowing for individual variation. Participants were selected through purposive sampling, focusing on those with prior experience of AI. Interviews continued until theoretical saturation was reached. Data analysis was inspired by grounded theory, using a systematic coding process. The findings reveal that consumer satisfaction with AI recommendations is influenced by added value, contextual relevance, and timing. Additionally, factors such as speed, efficiency, quality responses, accessibility, adaptive empathy, communication style and humour play crucial roles. These components demonstrate how AI personalisation can strengthen consumer satisfaction by tailoring recommendations and interactions to individual tastes and preferences.

Beside all the technical challenges concerning sensor quality and control algorithms one of the main issues related to the introduction of advanced driver assistance systems (ADAS) constitutes the human-machine interaction. This covers not only the physical interface between the driver and the system but also the understanding and cognitive model the driver needs to operate the system. The explorative analysis of a long-term field study of the use of ACC, was aimed at identifying characteristics of the learning process and their potential implications for conceptualising novel displays to increase, particularly in the early phases, usability and safety of the system through the adaptation of information to the drivers. The analysis of the learning aspects derived from drivers’ interaction with the system enabled the identification of learning aims for the usage of an ACC system and an objective classification of observable behaviours from which different levels of skill can be interpreted. It was concluded that by responding to the difficulties met by users in the actual situation and by adapting the information to the drivers’ experience, drivers’ learning progress could be accelerated through better comprehensibility and predictability of the system. To this aim, two innovative help-systems were conceived, implemented and evaluated in terms of drivers driving behaviour and interactions with the ACC system, in the BMW fixed-base driving simulator. A learn-adaptive, multi-modal, on-line tutor system that covered interactions with the system at every level of the driving task (Reichart, 2001) for which learning must be effectuated, was tested with 11 participants. A personalised learning model of the driver was used to relate the drivers’ prior usage of the system and his situational experience, to give the driver additional advice and explanation in order to shorten the learning period. A main effect was found between the experimental groups’ understanding of the system and in participants’ ability to predict when to reclaim control of the system, as measured by the reduction in unnecessary interventions and reduced number of panic reactions. The use of cognitive apprenticeship methods (Cognition and Technology Group at Vanderbilt, 1993) on an online adaptation of feedback showed a positive influence on the learning process, increasing the speed of the learning process towards the acquisition of skill. The second experiment’s objective was to develop an interface that most effectively helped drivers learn to predict the need to reclaim control and the appropriate sensitivity of response in take-over situations. Drivers interactions with a didactic, two-step warning display, based on a time algorithm that was personalised to drivers maximum preferred deceleration level, was tested with 24 participants. Display effects were observed in time-to-collision, reaction times, the number of false alarms (unnecessary driver interventions) and misses (collision or near collisions). Significant differences were also found in distance error, adequate deceleration rates, panic braking and reaction times on the peripheral detection task. These results were also largely supported by the subjective measures. The proposed concepts have shown methods of reducing the ADAS learning phase and accelerating drivers behaviour to a skill level. The theoretical and empirical work described in this thesis plays an important role in deriving recommendations for systems that reduce the amount of learning demand on the driver and eliminates learnability issues that can lead to safety-critical traffic situations.

Effective methods for information access are of the greatest importance for our modern lives – particularly with respect to handheld devices. Personalisation is one such method which models a user’s characteristics to deliver content more focused to the user’s needs. The emerging area of sophisticated mobile computing devices has started to inspire new forms of personalised systems that include aspects of the person’s contextual environment. This thesis seeks to understand the role of personalisation and context, to evaluate the effectiveness of context for content personalisation and to investigate the event and map content domain for mobile usage. The work presented in this thesis has three parts: The first part is a user experiment on context that investigated the contextual attributes of time, location and interest, with respect to participants’ perception of their usefulness. Results show highly dynamic and interconnected effects of context on participants’ usefulness ratings. In the second part, these results were applied to create a predictive model of context that was related to attribution theory and then combined with an information retrieval score to create a weighted personalisation model. In the third part of this work, the personalisation model was applied in a mobile experiment. Participants solved situational search tasks using a (i) non-personalized and a (ii) personalized mobile information system, and rating entertainment events based on usefulness. Results showed that the personalised system delivered about 20% more useful content to the mobile user than the non-personalised system, with some indication for reduced search effort in terms of time and the amount of queries per task. The work presented provides evidence for the promising potential of context to facilitate personalised information delivery to users of mobile devices. Overall, it serves as an example of an investigation into the effectiveness of context from multiple angles and provides a potential link to some of the aspects of psychology as a potential source for a deeper understanding of contextual processes in humans.

The rapid growth of digital video content in recent years has imposed the need for the development of technologies with the capability to produce condensed but semantically rich versions of the input video stream in an effective manner. Consequently, the topic of Video Summarisation is becoming increasingly popular in multimedia community and numerous video abstraction approaches have been proposed accordingly. These recommended techniques can be divided into two major categories of automatic and semi-automatic in accordance with the required level of human intervention in summarisation process. The fully-automated methods mainly adopt the low-level visual, aural and textual features alongside the mathematical and statistical algorithms in furtherance to extract the most significant segments of original video. However, the effectiveness of this type of techniques is restricted by a number of factors such as domain-dependency, computational expenses and the inability to understand the semantics of videos from low-level features. The second category of techniques however, attempts to alleviate the quality of summaries by involving humans in the abstraction process to bridge the semantic gap. Nonetheless, a single user’s subjectivity and other external contributing factors such as distraction will potentially deteriorate the performance of this group of approaches. Accordingly, in this thesis we have focused on the development of three user-centred effective video summarisation techniques that could be applied to different video categories and generate satisfactory results. According to our first proposed approach, a novel mechanism for a user-centred video summarisation has been presented for the scenarios in which multiple actors are employed in the video summarisation process in order to minimise the negative effects of sole user adoption. Based on our recommended algorithm, the video frames were initially scored by a group of video annotators ‘on the fly’. This was followed by averaging these assigned scores in order to generate a singular saliency score for each video frame and, finally, the highest scored video frames alongside the corresponding audio and textual contents were extracted to be included into the final summary. The effectiveness of our approach has been assessed by comparing the video summaries generated based on our approach against the results obtained from three existing automatic summarisation tools that adopt different modalities for abstraction purposes. The experimental results indicated that our proposed method is capable of delivering remarkable outcomes in terms of Overall Satisfaction and Precision with an acceptable Recall rate, indicating the usefulness of involving user input in the video summarisation process. In an attempt to provide a better user experience, we have proposed our personalised video summarisation method with an ability to customise the generated summaries in accordance with the viewers’ preferences. Accordingly, the end-user’s priority levels towards different video scenes were captured and utilised for updating the average scores previously assigned by the video annotators. Finally, our earlier proposed summarisation method was adopted to extract the most significant audio-visual content of the video. Experimental results indicated the capability of this approach to deliver superior outcomes compared with our previously proposed method and the three other automatic summarisation tools. Finally, we have attempted to reduce the required level of audience involvement for personalisation purposes by proposing a new method for producing personalised video summaries. Accordingly, SIFT visual features were adopted to identify the video scenes’ semantic categories. Fusing this retrieved data with pre-built users’ profiles, personalised video abstracts can be created. Experimental results showed the effectiveness of this method in delivering superior outcomes comparing to our previously recommended algorithm and the three other automatic summarisation techniques.

This mixed method study sought to explore the perceptions of key stakeholders in education, on the role and contribution of ICT in Scottish secondary schools towards generic skills development among pupils for post school transitions. The timing of this study coincided with a period characterised by contextual pressures globally, marked with technology changes, youth unemployment and curriculum reviews. A review of literature was conducted systematically to evaluate the explicit permeation of ICT in Scottish schools. A sequential mixed method design was adopted for the two phased study commencing with a convenience sampling technique for the first phase, involving 1364 upper secondary school pupils from all eight schools, 64 teachers and the 17 employers in one local Council in Scotland. A purposive sampling technique was applied to select two sample schools for the second phase, based on best use and practices of ICT. Questionnaires were administered online and in person at the first phase, followed by a semi structured interview at the second phase. SPSS was used for descriptive statistics, correlation analysis and one way Anova, while Nvivo 10 software was used for thematic analysis from the interview transcript. The study offers a framework for personalisation starting with identification of pupils’ ability and ICT skill level at inception classes, followed by a personalised learning design incorporating pupils’ interest, ability and post school destination. The study also proposes separate roles for teachers and policy makers in order to maintain teachers’ autonomy, as policy makers’ interference has been identified to have an impact on teachers’ professionalism, effectiveness and confidence necessary for imparting generic skills in pupils. A series of recommendations are provided for future research, including a longitudinal evaluation of generic skills acquired from individual school subjects through the upper school years to post school destination, to ascertain effective transfer and sustainability of generic skills.

The major objective of this study is to explore empirically the effects of permission, interactivity, vividness and personalisation upon attitude, behavioural intention and recommendation to e-mail marketing (the latter two variables being proxies for behaviour). The proposed model is based on the integrated framework of Fishbein and Ajzen's Theory of Reasoned Action (TRA), Triadis's Theory of Planned Behaviour (TPB) and Rettie's 2002 Basic E-mail Response Process Model. For data collection, qualitative and quantitative studies were used. The qualitative results from four semi-structured interviews reveal New Zealand enterprises' strong trust in permission-based e-mail marketing and how they implement it as one of their marketing strategies. The quantitative component presents and empirically tests the proposed model in terms of a personalisation (presence/absence), interactivity (low/high) and vividness (low/medium/high) (2*2*3) between-subjects factorial design, where subjects were exposed to an e-mail advertisement for a mobile phone. From 650 responses collected by clicking on an e-mail link through an online web survey, the data was analysed with analysis of covariance (ANCOVA). Based on strong suggestions in the literature and findings in the qualitative study on the importance of permission-based marketing, attitude toward permission e-mail was examined as one of the dependent variables in the quantitative study. Results reveal similarities and differences in the effects of interactivity, vividness and personalisation respectively between the low and high attitude toward permission based e-mail marketing groups. Although significant effects of interactivity on attitude and behavioural intention were observed, the nature of those effects proved contrary to the author's expectation. In terms of vividness, results showed significant effects on attitude and behavioural intention in both groups as anticipated. Conversely, personalisation was shown to have no effect on attitude and behavioural intention in any group, however, a positive effect on response rates was indicated. Two three-way interaction effects between interactivity, vividness and personalisation on attitude toward brand and friend recommendation were found only in the high group. This study strongly encourages e-mail marketers to respect their customers' privacy and to employ a permission-based marketing concept within their business strategy. The design of the e-mail (moderate to high vividness) and personalisation (use of recipient's name) are indicated to have a positive impact on the effectiveness of an e-mail ad. Future research should examine a permission-based marketing construct as a longitudinal study, and investigate personalisation at a higher level (based on recipients' preferences).

Personalisation of content is a frequently used technique intended to improve user engagement and provide more value to users. Systems designed to provide recommendations to users are called recommender systems and are used in many different industries. This study evaluates the potential of personalisation in a media group primarily publishing local news, and studies how information stored by the group may be used for recommending content. Specifically, the study focuses primarily on content-based filtering by article tags and user grouping by demographics. This study first analyses the data stored by a media group to evaluate what information, data structures, and trends have potential use in recommender systems. These insights are then applied in the implementation of recommender systems, leveraging that data to perform personalised recommendations. When evaluating the performance of these recommender systems, it was found that tag-based content selection and demographic grouping each contribute to accurately recommending content, but that neither method is sufficient for providing fully accurate recommendations.

The aim of this research was to specify and develop a service that is capable of delivering personalisable running shoes with mass appeal. Current sports footwear personalisation services focus primarily on aesthetic design via the internet. Aesthetics do not appear to be the consumers primary interest when purchasing running shoes and a large number are also reluctant to purchase online; preferring to purchase from specialist running stores where they receive the advice needed and can directly interact with the product. After reviewing the literature, it was hypothesised that the implementation of a primarily comfort and performance running shoe personalisation service with an in store fitting element, utilising additive manufacturing as an enabling technology, would give the greatest opportunity for success. Survey methods and store visits were employed that targeted both qualitative and quantitative data, exploring consumer running shoe purchase preferences, running shoe use and opinions of current personalisation services. The findings from these studies supported the previously stated hypothesis and enabled the specification of a suitable service. Subsequently, the focus of this research was the development of a toolkit, a computer-based system that enables the consumer to make their selections, the core of most of the current services. Experts in biomechanics and additive manufacturing were consulted to ensure that a feasible yet innovative solution was delivered. The resultant toolkit prototype (www.yourstep.co.uk) was tested formatively, using multiple methods and summatively with a large sample. Using the toolkit was considered an enjoyable, intuitive experience; a large percentage (69%) of summative testing participants would consider purchasing personalised running shoes using this method. The approach adopted to specify and develop this service provides a framework, based upon empirical research, for those looking to implement a practical running shoe personalisation service that meets their consumers requirements.

This thesis investigates the use of static, adaptive, adaptable and mixed-initiative approaches to the personalisation of content and graphical user interfaces (GUIs). This empirical study consisted of three experimental phases. The first examined the use of static, adaptive, adaptable and mixed-initiative approaches to web content. More specifically, it measured the usability (efficiency, frequency of error occurrence, effectiveness and satisfaction) of an e-commerce website. The experiment was conducted with 60 subjects and was tested empirically by four independent groups (15 subjects each). The second experiment examined the use of adaptive, adaptable and mixed-initiative approaches to GUIs. More specifically, it measured the usability (efficiency, frequency of error occurrence, effectiveness and satisfaction) in GUI control structures (menus). In addition, it investigated empirically the effects of content size on five different personalised menu types. In order to carry out this comparative investigation, two independent experiments were conducted, on small menus (17 items) and large ones (29 items) respectively. The experiment was conducted with 60 subjects and was tested empirically by four independent groups (15 subjects each). The third experiment was conducted with 40 subjects and was tested empirically by four dependent groups (5 subjects each). The aim of the third experiment was to mitigate the drawbacks of the adaptive, adaptable and mixedinitiative approaches, to improve their performance and to increase their usability by using multimodal auditory solutions (speech, earcons and auditory icons). The results indicate that the size of content affects the usability of personalised approaches. In other words, as the size of content increases, so does the need of the adaptive and mixed-initiative approaches, whereas that of the adaptable approach decreases. A set of empirically derived guidelines were also produced to assist designers with the use of adaptive, adaptable and mixed-initiative approaches to web content and GUI control structure.

At large sporting events (LSEs), e.g. football matches and athletics events, the user experience has been shown to be highly variable (Nilsson, 2004; Nilsson et al. 2004). Reported problems include a lack of social interaction with fellow spectators, and insufficient relevant information on the events or the sporting action taking place (Nilsson, 2004; Nilsson et al. 2004; Esbjornsson et al. 2006; Jacucci et al. 2005). A possible solution is personalisation, making the mobile application adapt to the user, ensuring that only relevant information is retrieved and presented in a way that is suitable. This thesis is devoted to studying the user experience related to mobile personalization at LSEs. It aims to investigate how personalized mobile applications at LSEs can render the user experience more active and engaging in a contextually, socially and culturally relevant way. The thesis reviews different theoretical approaches to help to understand the concepts of interest e.g. personalization and user experience (Chapter 2). Research methods are also discussed including the challenge of adapting user-centred methods into the Chinese culture (Chapter 3). This thesis investigates the user experience of mobile personalization at LSEs by following the circle of user-centred research: It starts to consider user requirements and user experience at LSEs and derives the usage patterns that personalized mobile applications could usefully support (Chapter 4). Then it explores the relevant contextual factors at LSEs which could be used to prescribe the behaviour of a personalizable mobile application (Chapter 5). Next, it describes the user-centred process used to design personalizable interfaces for mobile applications used at LSEs. Four key elements of design are considered: content, conceptual, interaction and presentation design (Chapter 6). The final outputs of the design process were two personalized mobile prototypes for Chinese users at LSEs. These included versions based on either (1) user-initiated or (2) system-initiated personalisation. Finally it investigates the impact on user experience of mobile personalization at LSEs in two empirical studies (a field experiment and a lab-based experiment) with these prototypes (Chapters 7 and 8). Mobile personalization is shown to result in an enriched user experience across a range of activities that a spectator would undertake at a large sporting event. The thesis discusses primarily the effective design of mobile personalization, the design implications at LSEs, user experience design, and research methods for Chinese users (Chapter 9). In conclusion (Chapter 10), specific contributions and avenues for future work are highlighted.