Human Behavior and Emerging Technologies最新文献

Innovative applications of human movement analysis, for example, for mitigating/slowing down certain pathological conditions, have recently emerged from the modeling and automated measurement of full-body expressive midlevel individual and group movement qualities, at a higher complexity level than movement qualities derived directly from physical signals, still not characterizing any gesture in a specific way. More in general, the availability of automated analysis techniques of midlevel expressive movement qualities can contribute to interaction design incorporating body-based performance practices inspired by artistic theories in dance and music. This work investigates how such practices and techniques can support embodied interaction design by enabling automated measuring of cues of leadership, cohesion, and fluidity in full-body movement in group settings. In particular, the dance-inspired scientific approach, the data collection protocol, and the analysis techniques adopted for assessing movement qualities connected to leadership and cohesion within the group and fluidity of the dancers’ full-body movement are described. Finally, future developments of this research are outlined.

The exponential growth of video-sharing platforms, exemplified by platforms like YouTube and Netflix, has made videos available to everyone with minimal restrictions. This proliferation, while offering a variety of content, at the same time introduces challenges, such as the increased vulnerability of children and adolescents to potentially harmful material, notably explicit content. Despite the efforts in developing content moderation tools, a research gap still exists in creating comprehensive solutions capable of reliably estimating users’ ages and accurately classifying numerous forms of inappropriate video content. This study is aimed at bridging this gap by introducing VideoTransformer, which combines the power of two existing models: AgeNet and MobileNetV2. To evaluate the effectiveness of the proposed approach, this study utilized a manually annotated video dataset collected from YouTube, covering multiple categories, including safe, real violence, drugs, nudity, simulated violence, kissing, pornography, and terrorism. In contrast to existing models, the proposed VideoTransformer model demonstrates significant performance improvements, as evidenced by two distinct accuracy evaluations. It achieves an impressive accuracy rate of (96.89%) in a 5-fold cross-validation setup, outperforming NasNet (92.6%), EfficientNet-B7 (87.87%), GoogLeNet (85.1%), and VGG-19 (92.83%). Furthermore, in a single run, it maintains a consistent accuracy rate of 90%. Additionally, the proposed model attains an F1-score of 90.34%, indicating a well-balanced trade-off between precision and recall. These findings highlight the potential of the proposed approach in advancing content moderation and enhancing user safety on video-sharing platforms. We envision deploying the proposed methodology in real-time video streaming to effectively mitigate the spread of inappropriate content, thereby raising online safety standards.

As more of our lives are spent using electronic devices, it comes as a natural deduction that those digital tools could be used to maintain people’s health. Gamified exercise or exergames are indeed promising means to motivate the population to get physically active and even cognitively active if paired with the appropriate games. Considering the global concern of an aging population which could benefit from both physical and cognitive stimulation, these tools appear to be an encouraging solution to keep the population healthier over time. This scoping review reports on the digital tools used in publications between January 2015 and December 2023 regarding the physical and cognitive stimulation of healthy elderly people. The search was conducted in PubMed, Web of Science, and ScienceDirect databases. Of the 1579 publications retrieved, a total of 68 publications were analyzed in this review. A wide variety of digital tools were used in the corpus for the combined physical and cognitive stimulation of the elderly. These tools can be categorized into six types of hardware: pressure plates, optical motion capture, inertial motion capture, virtual reality, ergometers, and driving simulators. The apparition of publications using virtual reality and an increase in publications using inertial motion capture in 2020 could be an indicator that digital tools used for cognitive and physical stimulation of the elderly are evolving. Another finding is the wide variety in evaluation tools used to monitor the outcomes of each protocol. A standardization of the testing process might be needed in order to improve comparisons between experiments.

This study explores the adoption and societal implications of an emerging technology such as Chat Generative Pre-Trained Transformer (ChatGPT) in higher education students. By utilizing a mixed-method framework, this research combines Rogers’ diffusion of innovation theory with sentiment analysis, offering an innovative methodological approach for examining technology adoption in higher educational settings. It explores five attributes—relative advantage, compatibility, ease of use, observability, and trialability—shaping students’ behavioral intentions toward ChatGPT. Sentiment analysis offers qualitative depth, revealing emotional and perceptual aspects, and introduces a gender-based perspective. The results suggest that five innovation attributes significantly impact the adoption rates and perceptions of ChatGPT, indicating its potential for transformative social change within the educational sector. Gen Zs viewed ChatGPT as innovative, compatible, and user-friendly, enabling the independent pursuit of educational goals. Consequently, the benefits provided by ChatGPT in education motivate students to use the tool. Gender differences were observed in the prioritization of innovation attributes, with male students favoring compatibility, ease of use, and observability, while female students emphasized ease of use, compatibility, relative advantage, and trialability. The findings have implications for understanding how technological innovations such as ChatGPT could be strategically diffused across different societal segments, especially in the academic context where ethical considerations such as academic integrity are paramount. This study underscores the need for a demographic-sensitive, user-centric design in generative artificial intelligence (AI) technologies.

The significance of innovation and the expectation for employees to exhibit innovative behavior have been heightened as a result of swift technological advancements and an evolving business landscape. The present research is aimed at examining the impact of organizational justice on fostering innovation in a dynamic business environment. Extending the previous literature which generally examined the combined impact of different facets of organizational justice, we employed the social cognitive theory framework to investigate the mechanism through which the three facets of organizational justice (distributive justice, procedural justice, and interactional justice) lead to employee innovative behavior through the mediating role of employees’ creative self-efficacy. Additionally, we examined the role of age as a pertinent boundary condition, an aspect often overlooked in the literature on creative self-efficacy and innovative behavior which is likely to augment our understanding of the potential mechanism driving innovative behavior. The sample comprises 320 individuals employed in the information technology industry. The data were collected in two waves, and subsequent analysis was conducted utilizing the Warp PLS 8 software. The present investigation employed partial least square (PLS)-based structural equation modeling (SEM) to conduct analysis and evaluate hypotheses. The results indicate that all three facets of organizational justice have a positive influence on employees’ creative self-efficacy, which subsequently manifests in their innovative behavior. Additionally, age has an impact on the relationship between creative self-efficacy and employee innovative behavior, which becomes less pronounced as employees get older. Theoretical contributions and practical implications for practitioners are discussed.

In today’s interconnected world, the widespread use of the Internet necessitates an understanding of factors influencing individuals’ ability to maintain a balanced relationship with technology. This study investigates digital life balance (DLB) by examining its associations with Internet social capital (ISC), loneliness, fear of missing out (FoMO), and anxiety levels. Five hundred and twenty participants (66% women; M_age = 30.12 years, SD = 12.46) took part in the data collection. Drawing upon the Psychology of Harmony and Harmonization framework, the study revealed negative correlations between DLB and ISC, loneliness, FoMO, and anxiety levels. Higher ISC was associated with lower DLB, suggesting that an extensive online network might lead to technological imbalance. Increased loneliness, FoMO, and anxiety were negatively associated with DLB, indicating possible disruptions between online and offline activities.

Mobile devices (e.g., tablets and smartphones) have been rapidly integrated into the lives of children and have impacted how children engage with digital media. The portability of these devices allows for sporadic, on-demand interaction, reducing the accuracy of self-report estimates of mobile device use. Passive sensing applications objectively monitor time spent on a given device but are unable to identify who is using the device, a significant limitation in child screen time research. Behavioral biometric authentication, using embedded mobile device sensors to continuously authenticate users, could be applied to address this limitation. This study examined the preliminary accuracy of machine learning models trained on iPad sensor data to identify the unique user of the device in a sample of children ages 6 to 11. Data was collected opportunistically from nine participants (8.2 ± 1.75 years, 5 female) in the sedentary portion of two semistructured physical activity protocols. SensorLog was downloaded onto study iPads and collected data from the accelerometer, gyroscope, and magnetometer sensors while the participant interacted with the iPad. Five machine learning models, logistic regression (LR), support vector machine, neural net (NN), k-nearest neighbors (k-NN), and random forest (RF), were trained using 57 features generated from the sensor output to perform multiclass classification. A train-test split of 80%–20% was used for model fitting. Model performance was evaluated using F1 score, accuracy, precision, and recall. Model performance was high, with F1 scores ranging from 0.75 to 0.94. RF and k-NN had the highest performance across metrics, with F1 scores of 0.94 for both models. This study highlights the potential of using existing mobile device sensors to continuously identify the user of a device in the context of screen time measurement. Future research should explore the performance of this technology in larger samples of children and in free-living environments.

Given the phenomenon of “financing is difficult and expensive” for MSEs, this paper empirically investigated the influencing mechanism of the credit demand side characteristics on the financing constraints of MSEs based on the information conveyance perspective. The conclusions show that MSEs in China are severely suffering from financing constraints and 57.17% and 50.00% of MSEs with credit demand have not applied for loans from formal and informal financing channels, respectively. In terms of enterprise characteristics, MSEs have low asset size, short establishment history, weak profitability, and lack of tools such as fixed assets, complete financial management system, professional technicians, and private brands to convey risk information to financing institutions, which are key factors resulting in their financing constraints. In terms of owner characteristics, young owners lack financing experience and convey higher risk information to financing institutions; therefore, owners’ age negatively influences the financing constraints of MSEs. These findings suggest that banks can use big data credit technology as a tool to obtain risk information about MSEs, and the government should implement diversified interventions to improve the information environment in financial markets. These findings provide empirical evidence for banks and governments to address the financing constraints of MSEs.

The fourth industrial revolution is bringing artificial intelligence (AI) into various workplaces, and many businesses worldwide are already capitalizing on AI assistants. Trust is essential for the successful integration of AI into organizations. We hypothesized that people have higher trust in human assistants than AI assistants and that people trust AI assistants more if they have more control over their activities. To test our hypotheses, we utilized a survey experiment with 828 participants from Finland. Results showed that participants would rather entrust their schedule to a person than to an AI assistant. Having control increased trust in both human and AI assistants. The results of this study imply that people in Finland still have higher trust in traditional workplaces where people, rather than smart machines, perform assisting work. The findings are of relevance for designing trustworthy AI assistants, and they should be considered when integrating AI technology into organizations.

The adoption of online learning modalities has increasingly become prevalent, particularly with the advent of COVID-19, aiming to ensure student access to learning materials. This significant shift towards offering online educational formats compels educational institutions to alter their approach and develop curricula to guarantee an optimal student experience and satisfaction within the online environment. The aim of this research is to comprehensively examine the key factors that significantly impact the satisfaction of undergraduate students with online learning in Vietnamese universities. The quantitative research methodology was implemented through the collection of surveys from a total of 437 Vietnamese students. Utilizing the PLS-SEM statistical approach, the findings reveal that technology, communication, course, outcome, and motivation for learning have significant positive influences on students’ satisfaction with online education during the COVID-19 pandemic, while the effect of instructors’ attitude and the sudden change from traditional to online classes have been found with as nonsignificant. Valuable implications and practical recommendations are suggested for educational organizations and institutions in Vietnam to enhance specific activities that promote students’ satisfaction with online learning and improve teaching methods provided by instructors.