Designing sustainable and scalable educational systems is a challenge. Artificial Intelligence (AI) offers promising solutions to enhance the effectiveness and sustainability of blended learning systems. This research paper focuses on the integration of the Chat Generative Pre-trained Transformer (ChatGPT), with a blended learning system. The objectives of this study are to investigate the potential of AI techniques in enhancing the sustainability of educational systems, explore the use of ChatGPT to personalize the learning experience and improve engagement, and propose a model for sustainable learning that incorporates AI. The study aims to contribute to the body of knowledge on AI applications for sustainable education, identify best practices for integrating AI in education, and provide insights for policymakers and educators on the benefits of AI in education delivery. The study emphasizes the significance of AI in sustainable education by addressing personalized learning and educational accessibility. By automating administrative tasks and optimizing content delivery, AI can enhance educational accessibility and promote inclusive and equitable education. The study’s findings highlight the potential benefits of integrating AI chatbots like ChatGPT into education. Such benefits include promoting student engagement, motivation, and self-directed learning through immediate feedback and assistance. The research provides valuable guidance for educators, policymakers, and instructional designers who seek to effectively leverage AI technology in education. In conclusion, the study recommends directions for future research in order to maximize the benefits of integrating ChatGPT into learning systems. Positive results have been observed, including improved learning outcomes, enhanced student engagement, and personalized learning experiences. Through advancing the utilization of AI tools like ChatGPT, blended learning systems can be made more sustainable, efficient, and accessible for learners worldwide.

Technological developments are increasingly sophisticated, so micro, small and medium enterprises (MSMEs) must maintain their business through digital markets. The main problem faced by MSMEs in Aceh province is the lack of use of social media as a medium for promoting or selling products online. Thus, this study analyzes the MSMEs' product marketing model, determines the factors that influence MSME labor productivity, and determines MSMEs' resilience strategies in entering the digital market. The research location is Aceh Province which consists of 23 districts/cities. The population in this study were all MSME actors in Aceh Province who were spread across districts/cities, using a purposive random sampling technique. The samples in the study were related agencies and MSMEs actors in Aceh Province, which are spread across 13 regencies/cities, namely Banda Aceh, Sabang, Lhokseumawe, Subulussalam, Langsa, Aceh Tamiang, East Aceh, North Aceh, Central Aceh, West Aceh, Aceh Singkil, Aceh Besar and Aceh Jaya. The results of the study show that (1) the marketing model that is used effectively is the marketing mix, namely the marketing mix, (2) the productivity of MSME workers is influenced by the level of education, age, work experience, gender and expertise or skills possessed by the workforce, (3) The MSMEs resilience strategy is dealing with the digital market can be pursued through government policies by providing training or assistance to business actors to increase product innovation and increase promotion or product sales online through various types of social media, such as Instagram, Facebook, WhatsApp, and market places other.

The Android operating system is the most used mobile operating system in the world, and it is one of the most popular operating systems for different kinds of devices from smartwatches, IoT, and TVs to mobiles and cockpits in cars. Security is the main challenge to any operating system. Android malware attacks and vulnerabilities are known as emerging risks for mobile devices. The development of Android malware has been observed to be at an accelerated speed. Most Android security breaches permitted by permission misuse are amongst the most critical and prevalent issues threatening Android OS security. This research performs several studies on malware and non-malware applications to provide a recently updated dataset. The goal of proposed models is to find a combination of noise-cleaning algorithms, features selection techniques, and classification algorithms that are noise-tolerant and can achieve high accuracy results in detecting new Android malware. The results from the empirical experiments show that the proposed models are able to detect Android malware with an accuracy that reaches 87%, despite the noise in the dataset. We also find that the best classification results are achieved using the RF algorithm. This work can be extended in many ways by applying higher noise ratios and running more classifiers and optimizers.

The major goal of this research is to examine how vlogging on YouTube affects the communication skills of Jordan teenagers with language and speech disorders. Fifty people, ranging in age from 13 to 18, participated in an eight-week vlogging intervention program designed to improve their communication skills. The results of the pre- and post-tests showed a statistically significant improvement in communicative competence, with the mean difference between the two measures being 10.5. Vlogging has a significant effect as an intervention because of its remarkable ability to actively engage participants in the creation of relevant content, the facilitation of authentic real-life communication experiences, the encouragement of creative and self-expressive expression, and the provision of individualized therapeutic approaches. Adolescents with speech and language disabilities have unique obstacles in communicating, and this study gives insight on the possible use of novel tools, such as vlogging, to address these issues.

With the hope of improving students' social interactions who have been diagnosed with Autism Spectrum Disorder (ASD) in Saudi Arabia, the current study set out to examine the effectiveness of peer-mediated therapies delivered through the ubiquitous social media platform Snapchat. Thirty kids with ASD and 15 generally developing peers participated in the study. Alterations in social communication difficulties and observable social interactions were evaluated before and after the intervention to determine its efficacy. The results of the research revealed significant improvements in both self-reported difficulties with social communication and the quality of participants' interpersonal relationships. These findings demonstrate the groundbreaking methodology's deep applicability and widespread cross-cultural significance. Individuals with ASD have shown to benefit greatly from individualized, technology-based therapy to improve their social interactions, as shown by this study.

The aim of this research was to evaluate the impact of decentralization and electronic participatory budgeting on managerial performance. Additionally, the study sought to investigate the management accounting system's role in strengthening the effect of decentralization and electronic participatory budgeting on managerial performance. This quantitative research involved 30 regional units, using primary data collected through questionnaires of 108 fund management officials. The findings of this study demonstrated that decentralization and electronic participatory budgeting both have a positive and significant effect on managerial performance. Furthermore, the management accounting system was found to act as a moderator between decentralization and performance, but not between electronic participatory budgeting and performance.

Tuberculosis (TB) is still a major public health concern in many regions of the world, including Indonesia's West Java Provinces. Accurate TB risk factor prediction can enhance overall TB control efforts by directing focused therapies. In this study, utilizing a combination of Negative Binomial Mixed Models (NBMMs) and Feed-Forward Neural Networks (FFNNs), we offer a unique method for the predictive modeling of TB risk variables. A variety of sociodemographic, behavioral, and environmental factors that are known to be linked to TB are included in the dataset utilized in this investigation. To correct for overdispersion and include both fixed and random effects in the model, we first fitted an NBMM major problem in epidemiological investigations is modeling count data with overdispersion, and the NBMM component of the model offers a versatile and effective framework for doing so. Following that, we include an FFNN component in the model, which helps us to detect relevant predictive features and alter the model's weights accordingly. Backpropagation methods are used by the FFNN to adjust model parameters and enhance accuracy. The resulting Negative Binomial Mixed Model Neural Network (NBMMNN) model has a high accuracy value of up to 0.944. Our research suggests that the NBMMNN model outperforms conventional models that are frequently used to predict TB risk factors. By contrast to simpler models, the NBMMNN model can capture complicated and nonlinear interactions between predictors and outcomes. Additionally, the inclusion of random variables in the model enables us to take into account potential sources of variability in the data as well as unmeasured confounding. This work emphasizes the opportunity to enhance TB risk prediction and control efforts by integrating NBMMs with FFNNs. In West Java Provinces and other comparable contexts, the NBMMNN model might be a helpful tool for identifying and resolving TB risk factors, guiding targeted interventions, and enhancing overall TB control efforts.

This study investigates the effect of perceived risks, i.e., financial risk, product risk, and convenience risk, as well as the COVID-19 pandemic situation on online shopping behavior among Malaysians. This study uses convenience sampling techniques and comprises 185 respondents who have experience buying online. In addition, the study setting was non-contrived, and data was gathered using a closed-ended questionnaire through an online survey. Descriptive analysis was conducted using SPSS version 25.0 software and SmartPLS version 3.2.8 to test the proposed hypotheses. This study found that perceived risk factors such as financial, product, and convenience risk did not influence online shopping behavior. In contrast, the COVID-19 pandemic positively influences online shopping behavior among consumers. It showed a new development in the theory of online shopping behavior, where users continue to make purchases despite being aware that there may be various risks due to the spread of COVID-19. The role of the ministry, business owners, and consumer associations needs to be given attention to form a sustainable electronic commerce system and protect the rights of consumers. This research can help consumers understand their rights.

The development of technology and smart mobile devices such as phones and tablets has changed the behavior of tourists when booking tourism services. Based on the technology acceptance model, this study aims to explore the factors influencing the intention to use mobile applications for accommodation booking among GENZ in Vietnam. The analysis of 218 users revealed that four factors influence the behavior of using mobile applications for booking: performance expectancy, effort expectancy, social influence, and hedonic motivation. In addition to identifying the factors affecting usage intention, this study also proposes implications to assist developers and providers in improving their applications and developing suitable product strategies for the future.

In a confirmatory study, researchers are expected to employ the covariance-based structural equation modeling (CB-SEM). One of the key presumptions when utilizing CB-SEM is that the data is multivariate normal. Nevertheless, a perfect normal distribution is rarely observed in real-life data. To resolve this, the unweighted least square (ULS) is designed to specifically deal with non-normal data in SEM. However, ULS often yields improper solutions like negative, or boundary estimates of unique variances since it considers measurement errors in observed variables. The disturbance in SEM is reflected in unique variance, which is random error due to unreliability or measurement error and reliable variation in the item that indicates unknown latent causes. Consequently, this can generate bias in indicator loadings estimates. As an action to disentangle this issue, the present study proposes the implementation of regularization parameters by adding small positive values to the variance-covariance matrix. The ratio of bias to variance in a model can be improved to obtain the best estimation performance. Pro-Active Monte Carlo simulation was used to produce multivariate non-normal data with designated sample sizes and population characteristics. The data were analyzed using R Programming Environment by employing “psych”, “MASS”, “foreign”, “mvrnonnorm”, “purr”, and “semTools” packages with 1000 replications to produce multivariate non-normal data. Next, the “lavaan” package was used for SEM and regularized SEM analyses. The outcome of this study proves the capability of regularized ULS to improve parameter estimation.