journal article
Download Only Collection
Home
doi: 10.1080/10447318.2023.2295693pmid: N/A
Abstract In response to the current problem of single sports plan and lack of long-term motivation in recommendation systems, a more intelligent personalized sports health recommendation system was designed by introducing Q-Learning (Quality Learning) algorithm. Firstly, user sports health data was collected, and the user model was constructed to track user sport preferences and historical behavior. Secondly, the sports environment was defined, including different types of sports activities, venues, and weather. Then, the reward function was formulated to reward and punish users based on their sports activities and goals, in order to maximize long-term health benefits. Finally, the Q-Learning algorithm was implemented to continuously iteratively learn and optimize user recommendation models to provide the best personalized sports recommendations. For personalized accuracy, indicators such as precision, recall, F1 value, MAE (Mean Absolute Error), and RMSE (Root Mean Square Error) were used to evaluate, while the system’s participation in sports, user satisfaction, long-term incentive effects, and overall health improvement were collected. The results showed that the average precision of the recommendation system on 10 different datasets was 88%, and the average AUC (Area Under Curve) was 96%, which was 6.7% higher than the SVD (Singular Value Decomposition) algorithm. The user’s sports persistence rate was improved by 25%, and the health score was improved by about 13.3%. These data not only reflect the superior performance of the recommendation system but also highlight its positive impact on long-term user motivation and overall health levels. The results indicate that the proposed personalized exercise health recommendation system, assisted by the Q-Learning algorithm, has significantly improved accuracy. Moreover, it offers users more intelligent and personalized exercise suggestions, effectively increasing long-term participation in physical activities and overall health levels.
Wang, Jun; Zheng, Wenzhi; Zhang, Lin; Wu, Yenchun Jim
doi: 10.1080/10447318.2024.2371690pmid: N/A
Abstract Nowadays, numerous enterprises are actively adopting electronic performance monitoring (EPM) systems with the goal of enhancing organizational performance by stimulating employee proactive behavior. However, some companies have reported that the EPM system didn't achieve the expected results and even led to the opposite. To address this paradoxical phenomenon, we employed psychological reactance theory to investigate the impacts of employee differentiate perceptions of EPM (developmental EPM [DEPM] and preventive EPM [PEPM]) on individual psychological and behavior reactance. By conducting a three-wave survey questionnaire among 446 corporate employees, we find that DEPM facilitates proactive behavior, while PEPM inhibits such behaviors; Second, psychological reactance mediates the relationships among DEPM, PEPM, and proactive behavior; Third, individual trait mindfulness positively (negatively) moderates the impact of DEPM (PEPM) on psychological reactance. This research elucidates the effects of EPM on proactive behavior, providing valuable information to support attempts to refine digitally driven monitoring models within organizations.
Chan, Gerry; Banire, Bilikis; Ataguba, Grace; Frempong, George; Orji, Rita
doi: 10.1080/10447318.2024.2372135pmid: N/A
Abstract In recent years, there has been growing research interest in aligning technological designs with users’ lived experiences. The goal of this work is to review existing work on the current state-of-the-art on incorporating individual and community values and beliefs into various kinds of interactive computerized technologies, emphasizing socio-cultural sensitivity. After screening 235 records, 45 papers were included in this review. Our research reveals that researchers are at the forefront of developing advanced socio-cultural digital tools and interactive educational platforms. They frequently employ techniques like collaborative dialogue facilitation, personalized linguistic support, and the integration of culturally significant design principles, such as cultural narratives and symbols. This commitment to technology’s transformative potential extends beyond education, making its mark in healthcare, social networks, finance, and other domains. We conclude by providing an overview of the questions that other researchers can investigate in the future for designing technologies that are socio-culturally sensitive. Future studies would benefit from a wider use of theories to account for the complexity of human behavior while designing socio-culturally sensitive technologies.
Anderton, Craig; Creed, Chris; Sarcar, Sayan; Theil, Arthur
doi: 10.1080/10447318.2024.2372151pmid: N/A
Abstract Exploration of virtual reality locomotion has a rich history, including in the creation of taxonomies categorising individual techniques. However, most existing research collects data from academic sources only, with both historic industry practitioner exploration and a state-of-the-art understanding of locomotion in commercial applications comparatively underexplored. This systematic software-level review of the complete locomotion options in 330 of the most used virtual reality applications released between 2016 and 2023 on the Steam, Meta, Oculus, Viveport, and SideQuest platforms highlights the trends and gaps that exist between industry and academic exploration. Results suggest a decline in the usage of teleportation, with the prevalence of titles containing at least one teleportation technique decreasing from 48% of those released in 2016 to 18% in 2023. Arm-tracked grabbing locomotion techniques such as climbing meanwhile are being increasingly adopted by practitioners, from almost unused in 3% of applications released in 2016 to over 30% in each year between 2020 and 2023. Additionally, although the tracking capabilities afforded by consumer-level head-mounted display hardware has resulted in a high exploration of room-scale tracking, the large academic focus on walking-based locomotion appears to not be shared by practitioners, where room-scale tracking instead is most often paired with conventional controller joystick sliding locomotion. Finally, temporal analysis results showing the growing number of locomotion techniques offered in an average application signifies the need for further accessibility-related locomotion research, particularly in areas beyond visual sickness mitigation. Our findings highlight the continuing evolution of locomotion in commercial virtual reality applications, with industry practitioner locomotion technique adoption rates displaying the divergent interests between industry and academia, in turn adding rigour to future locomotion selections across both domains.
Eltanbouly, Somaya; Halabi, Osama; Qadir, Junaid
doi: 10.1080/10447318.2024.2374091pmid: N/A
Abstract The concept of the Metaverse has sparked great interest as a futuristic virtual space that provides immersive experiences and social interactions through digital avatars. However, using avatars in the Metaverse raises privacy concerns that require innovative solutions to ensure the safety of users. In this article, we conducted a systematic review using the PRISMA method to identify work discussing privacy issues related to avatars in the Metaverse and efforts to provide safer virtual environments for users. Our review revealed two main avatar-related privacy issues: threats related to the user’s identity, such as the disclosure of personal details, and social threats, such as harassment. We also reviewed different proposed solutions to these problems, categorized into three main groups: altering user representation, providing safety options to users, and leveraging AI techniques to detect and mitigate issues. While these solutions promise a safer Metaverse for users, there are inherent limitations that require further advancements. To fill the existing research gap and create a safer Metaverse, we suggest improving safety features for users, finding a balance between user experience and privacy, increasing the use of AI to create safer environments while considering user concerns, and enhancing reporting methods available in the Metaverse. Our review emphasizes the need for more advanced research and development to tackle avatar privacy challenges in the Metaverse.
Gao, Wei; Jiang, Ning; Guo, Qingqing
doi: 10.1080/10447318.2024.2375685pmid: N/A
Abstract Despite the growing research interest in facial recognition payment (FRP), the factors that influence the intention to switch to FRP have received limited attention. Grounded in status quo bias theory, this study explores predictors of users’ intention to switch from QR code payment to FRP through an online survey. The empirical findings based on 1,244 responses indicate that the need for uniqueness negatively affects embarrassment, privacy concern, and inertia and positively affects switch intention. Further, embarrassment and privacy concern are both positively related to inertia and negatively related to switch intention, and inertia significantly reduces switch intention. Through multi-group analysis, this study also finds that users with experience using services enabled by facial recognition technology are more willing to switch to FRP. This study enriches the FRP literature by highlighting the roles of inertia and the need for uniqueness and provides several implications for FRP practitioners.
Fetrati, Hemad; Chan, Gerry; Orji, Rita
doi: 10.1080/10447318.2024.2376808pmid: N/A
Abstract There is a rising interest in chatbots dedicated to enhancing sexual health. However, there is limited research on the effectiveness of these chatbots, and the current literature lacks sufficient exploration of gaps and patterns in this field. In this review, we provided an overview of the state-of-the-art research conducted on sexual health chatbots, with the goal of identifying prevalent trends, design patterns, and features. In addition, we investigated existing research gaps, challenges, and shortcomings in the landscape of sexual health chatbots. Further, we proposed potential enhancements and directions for future research and development to create more effective chatbots in this field. A systematic search and screening of the literature from the past decade (2013–2023), extracted from seven databases, yielded a total of 1040 studies, out of which 29 articles were included in the final review following screening. The findings suggest that chatbots are usable and effective tools in sexual health education, persuasion, and assistance that are appreciated for their confidentiality, efficiency, and 24/7 availability. However, their performance is hindered by limitations such as restricted scope of knowledge and challenges in understanding user inputs. Additionally, constraints such as text-only input/output modalities and a predominant reliance on the English language limit their accessibility and acceptability. There is also a crucial need for more research in low-income or lower-middle-income countries, where individuals require increased sexual health education and support.
doi: 10.1080/10447318.2024.2381929pmid: N/A
Abstract Saliency maps can explain how deep neural networks classify images. But are they actually useful for humans? The present systematic review of 68 user studies found that while saliency maps can enhance human performance, null effects or even costs are quite common. To investigate what modulates these effects, the empirical outcomes were organised along several factors related to the human tasks, AI performance, XAI methods, images to be classified, human participants and comparison conditions. In image-focused tasks, benefits were less common than in AI-focused tasks, but the effects depended on the specific cognitive requirements. AI accuracy strongly modulated the outcomes, while XAI-related factors had surprisingly little impact. The evidence was limited for image- and human-related factors and the effects were highly dependent on the comparisons. These findings may support the design of future user studies by focusing on the conditions under which saliency maps can potentially be useful.
Wang, Wei; Zhu, Yeshan; Wang, Qingli; Jiao, Haoyang; Qu, Jue
doi: 10.1080/10447318.2024.2383028pmid: N/A
Abstract In response to the challenge of high cognitive pressure and difficulty for commanders in cross-layer operations during the transition from traditional two-dimensional command and control system interfaces to mixed reality human-computer interaction interfaces, this paper conducts research on the information fusion display method for the human-computer interaction interface of the mixed reality command and control system. First, based on the findings of previous research, we developed a five-layer human-computer interaction interface for a mixed reality command and control system in typical combat scenarios. An evaluation experiment was designed and the resulting data analyzed. This analysis revealed that there are problems with low work efficiency and high cognitive load in the information acquisition process in cross-layer interaction operations. Consequently, we conducted research into the methods of integrating and displaying interactive interface information, integrating and displaying interactive and display interface information, and integrating and displaying complex situation interface information. The research findings indicate that: (1) The optimal display ratio for mixed reality 2D interface integration is 3:2. (2) The optimal display scheme for mixed reality 2D interface fusion is a combination of the main and secondary interfaces, with the main interface table displaying global information and the secondary interface displaying accurate information. (3) The optimal display scheme for mixed reality 2D and 3D interface fusion is the display of overall class information in 2D and the accurate identification of class information in 3D. The findings of this research can be applied to the design of human-computer interaction interfaces for mixed reality command and control systems in complex battlefield environments.
Showing 1 to 10 of 51 Articles