•We first analyze the shortages of the existing similarity measures in collaborative filtering.•And second, we propose a new user similarity model to overcome these drawbacks.•We compare the new ...model with many other similarity measures on two real data sets.•Experiments show that the new model can reach better performance than many existing similarity measures.
Collaborative filtering has become one of the most used approaches to provide personalized services for users. The key of this approach is to find similar users or items using user-item rating matrix so that the system can show recommendations for users. However, most approaches related to this approach are based on similarity algorithms, such as cosine, Pearson correlation coefficient, and mean squared difference. These methods are not much effective, especially in the cold user conditions. This paper presents a new user similarity model to improve the recommendation performance when only few ratings are available to calculate the similarities for each user. The model not only considers the local context information of user ratings, but also the global preference of user behavior. Experiments on three real data sets are implemented and compared with many state-of-the-art similarity measures. The results show the superiority of the new similarity model in recommended performance.
Purpose/Significance Under the background of the rapid development of the new generation of information technology, the policy supports the smart health care industry, and all kinds of smart health ...care products are constantly popularized and applied. Exploring the practical issue of elderly users using smart health care products is of great significance for China to carry out smart actions to help the elderly and build a digital inclusive old-age society. Method/Process Based on the text information data such as news reports, product reviews and in-depth interviews, this paper adopted the grounded theory method, and formed 3 relational categories, 31 preliminary categories and 69 initial concepts through three-stage coding, and constructed a model of influencing factors of elderly users’ use of smart health care products. Result/Conclusion The research showed that the aging degree, product use guidelines and product safety design affect the psychological perception of elderly users, and individual char
User engagement has become a much-cited construct in human-computer interaction (HCI) design and evaluation research and practice. Constructed as a positive and desirable outcome of users' ...interactions, more frequent and longer interactions are considered evidence of engagement. Disengagement, when discussed, is considered a best avoided outcome of technology use or a solution to problematic technology use. In the case of the former, disengagement may signal usability issues or user disinterest, while the latter emphasizes that some engaging interactions can result in negative consequences (e.g., addiction) for end-users. In this paper, we draw upon examples from HCI research and digital tools to present a more nuanced understanding of the symbiotic relationship between engagement and disengagement in order to propose a new definition and novel ways to model disengagement. Further, we challenge generalizations that dichotomize engagement (positive, continuous, accompanied by high interactivity and beneficial to end-users) and disengagement (negative, stopping use or detrimental use) and invite readers to interpret engagement in the context of desirability with respect to users' goals and perceived agency. We concluded with implications that invite the reader to make space for disengagement and move beyond usage data in the evaluation of engagement. This paper is a call to step away from the practice of engagement-for-engagement's sake, and to reflect on whether and when engagement is meaningful and desirable for end users.
•User engagement is a desired outcome in human-computer interaction (HCI) research.•Less attention is paid to disengagement, though it is often perceived negatively.•We challenge prevalent fallacies of (dis)engagement in HCI design and evaluation.•We propose a definition of disengagement that takes into account user agency.•We model disengagement as a necessary part of the engagement cycle.
Over the last decade, we have seen an increasing number of solutions for distributed user interfaces (DUIs). This paper provides a detailed overview of existing DUI approaches and classify the ...different solutions based on the granularity of the distributed UI components, the supported interaction space as well as their support for the distribution of state. After the analysis of existing solutions, we discuss a DUI scenario and derive a number of requirements for end-user DUI development. We propose an approach where users can author their customised user interfaces based on a hypermedia metamodel and the concept of active components. We further discuss possibilities for the configuration and sharing of customised distributed user interfaces by end users where the focus is on an authoring rather than a programming approach.
Identifying and gaining access to lead users (LUs) in the market is very costly and time-consuming. To enable more efficient access to LUs, this study examines how the proportion of embedded lead ...users (ELUs) of the organization as employees differs from that of LUs in the market as consumers. An organizational survey and a survey of consumers were conducted in the travel market, and differences in the distribution of lead userness were examined based on the samples obtained from these surveys. The results indicate that the proportion of individuals with high lead userness is higher within the organization than in the market. However, no significant differences in lead userness within the organization was found according to employment type.
Firms are increasingly opening up their innovation efforts to allow users to tap into the benefits they can offer, such as mobile data service (MDS) innovation on iOS and Google Android platforms. ...For this purpose, platforms typically provide toolkits to facilitate user participation, aiming to create an ecosystem for sustainable innovation. However, with the barriers to user innovation and attrition of existing innovators, it could be challenging for firms to attract and sustain users’ MDS innovation. With the possible benefits from user innovation, and considering the challenges faced, firms need to understand how to influence potential user innovators to take part and to encourage extant user innovators to innovate again. However, there is a lack of comprehensive research and understanding of what drives users’ intentions to innovate services and the differences in the antecedents of such intention between potential and actual user innovators. Further, although prior studies have suggested that toolkits can support user innovation, little research has theorized and empirically tested their influence. Motivated thus, this study proposes a model based on (1) user innovation theory to explain the antecedents (including toolkit support) of user MDS innovation intention and (2) construal level theory to explain the differential effects of the antecedents for actual and potential user innovators. We tested the model through survey data from potential and actual MDS user innovators on Google Android and iOS platforms. We find that trend leadership and anticipated extrinsic reward influence both potential and actual user innovators’ intentions to innovate. However, anticipated recognition and toolkit support affect only actual user innovators, while anticipated enjoyment affects only potential user innovators. Interestingly, toolkit support strengthens the influence of anticipated enjoyment for actual user innovators but weakens its influence for potential user innovators. Further, potential user innovators value anticipated extrinsic rewards less than actual innovators do. The implications for research and practice are discussed.
Involving and engaging people with intellectual disabilities on issues relating to their mental wellbeing is essential if relevant tools and solutions are to be developed. This research explores how ...inclusive and participatory co-design techniques and principles can be used to engage people with intellectual disabilities in designing innovations in mental wellbeing tangible technologies. In particular, individuals with intellectual disabilities participated in a co-design process via a series of workshops and focus groups to design tangible interfaces for mental wellbeing as their wellbeing challenges are often diagnostically overshadowed. The workshops helped participants explore new technologies, including sensors and feedback mechanisms that can help monitor and potentially improve mental wellbeing. The adopted co-design approach resulted in a range of effective and suitable interfaces being developed for varying ages.
We present ilastik, an easy-to-use interactive tool that brings machine-learning-based (bio)image analysis to end users without substantial computational expertise. It contains pre-defined workflows ...for image segmentation, object classification, counting and tracking. Users adapt the workflows to the problem at hand by interactively providing sparse training annotations for a nonlinear classifier. ilastik can process data in up to five dimensions (3D, time and number of channels). Its computational back end runs operations on-demand wherever possible, allowing for interactive prediction on data larger than RAM. Once the classifiers are trained, ilastik workflows can be applied to new data from the command line without further user interaction. We describe all ilastik workflows in detail, including three case studies and a discussion on the expected performance.
•M-Banking is one of the most promising technologies that could prove to have considerable value to both banks and customers.•This study investigates factors that could predict the use of M-Banking, ...customer satisfaction and customer loyalty.•This study proposes a comprehensive conceptual model that clarifies the use of M-Banking from the perspective of Saudi users.•A questionnaire survey was conducted to collect the required data from convenience sampling of Saudi bank customers.•This study would consider the adoption of numeric data in order to inferentially analyse them using SEM.
Mobile banking is one of the most promising technologies that has emerged in recent years and could prove to have considerable value to both banks and customers. Thus, this study recognises the need to test the main factors that could predict the use of mobile banking as well as how using such a system could contribute to both customer satisfaction and customer loyalty. The conceptual model of this study combines two models (i.e. UTAUT2 and the D&M IS Success Model). A questionnaire survey was conducted to collect the required data from convenience sampling of Saudi bank customers. The main factors – performance expectancy, price value, facilitating conditions, hedonic motivation, habit, system quality and service quality – were found to have a significant impact on actual use behaviour. This study was cross-sectional, therefore future studies should implement longitudinal studies in order to re-collect the findings. Further, this study adopted convenience sampling of Saudi M-Banking users. This may adversely impact the issue of generalisability to the whole population. The gap in the M-Banking literature in Saudi Arabia would be bridged by proposing a comprehensive conceptual model that scrupulously clarifies the use of M-Banking from the perspective of Saudi users. Furthermore, this study would consider the adoption of numeric data in order to inferentially analyse them using SEM. This in turn would assist in generalising the findings to the whole Saudi population.
Published research on smart homes and their users is growing exponentially, yet a clear understanding of who these users are and how they might use smart home technologies is missing from a field ...being overwhelmingly pushed by technology developers. Through a systematic analysis of peer-reviewed literature on smart homes and their users, this paper takes stock of the dominant research themes and the linkages and disconnects between them. Key findings within each of nine themes are analysed, grouped into three: (1) views of the smart home—functional, instrumental, socio-technical; (2) users and the use of the smart home—prospective users, interactions and decisions, using technologies in the home; and (3) challenges for realising the smart home—hardware and software, design, domestication. These themes are integrated into an organising framework for future research that identifies the presence or absence of cross-cutting relationships between different understandings of smart homes and their users. The usefulness of the organising framework is illustrated in relation to two major concerns—privacy and control—that have been narrowly interpreted to date, precluding deeper insights and potential solutions. Future research on smart homes and their users can benefit by exploring and developing cross-cutting relationships between the research themes identified.
PDF
