Text Clustering consists of grouping objects of similar categories. The initial centroids influence operation of the system with the potential to become trapped in local optima. The second issue pertains to the impact of a huge number of features on the determination of optimal initial centroids. The problem of dimensionality may be reduced by feature selection. Therefore, Wind Driven Optimization (WDO) was employed as Feature Selection to reduce the unimportant words from the text. In addition, the current study has integrated a novel clustering optimization technique called the WDO (Wasp Swarm Optimization) to effectively determine the most suitable initial centroids. The result showed the new meta-heuristic which is WDO was employed as the multi-objective first time as unsupervised Feature Selection (WDOFS) and the second time as a Clustering algorithm (WDOC). For example, the WDOC outperformed Harmony Search and Particle Swarm in terms of F-measurement by 93.3%; in contrast, text clustering's performance improves 0.9% because of using suggested clustering on the proposed feature selection. With WDOFS more than 50 percent of features have been removed from the other examination of features. The best result got the multi-objectives with F-measurement 98.3%.

This study aimed to determine the impact of liquidity risk on financial performance of Jordanian banks, where liquidity risk was measured by (Liquidity ratio, net working capital, cash and investment ratio to total deposits), and financial performance was also measured through the index (return on assets) and the modifying variable (bank size) measured through the natural logarithm of total assets was also added. To achieve the objectives of the study, the analytical quantitative approach was adopted. The study community consisted of all 13 commercial banks listed on the Amman Stock Exchange. All banks in the study community were selected as a study sample using the comprehensive survey method, and the statistical analysis program (SPSS) was used to test the study hypotheses. Based on the results of the statistical analysis, it was found that there was an impact of liquidity risk on financial performance measured by return on assets in Jordanian commercial banks listed on Amman Stock Exchange, and there was an impact for each of (current liquidity ratio, net working capital, cash and investment ratio to total deposits) on financial performance measured by return on assets in Jordanian commercial banks listed on Amman Stock Exchange. It was also found that the size of the bank contributes to modifying the effect of liquidity risk on financial performance measured by return on assets in Jordanian commercial banks listed on Amman Stock Exchange. The study concluded a set of recommendations, the most important of which are: commercial bank administrations should increase interest in exploiting their liquidity within acceptable risk limits to reach optimal ratios for financial performance by balancing the returns to be achieved with the potential risks of such expenses in a way that ensures the positive impact of liquidity risk on the financial performance of those banks.

As the workforce worldwide goes through a transformative shift towards remote work, this paper discusses the positive effects of this quite flexible work arrangement on team’s innovation performance (TIP) in multinational, non-governmental organizations (NGOs). Adopting cross-sectional, quantitative research design, empirical data were collected through a survey of 268 employees of multinational NGOs operating in Jordan. The collected data were, then, analyzed using structural equation modeling. The results of the analysis showed that remote work has significant, positive effects on TIP in NGOs. Of the various remote work features investigated, spatial flexibility has the highest effect. The study results contribute to the ongoing discourse on the future of the work styles and have implications for leaders, policymakers, and practitioners who seek promoting innovation in multinational NGOs.

With the increasing prevalence of network intrusions, the development of effective network intrusion detection systems (NIDS) has become crucial. In this study, we propose a novel NIDS approach that combines the power of long short-term memory (LSTM) and attention mechanisms to analyze the spatial and temporal features of network traffic data. We utilize the benchmark UNSW-NB15 dataset, which exhibits a diverse distribution of patterns, including a significant disparity in the size of the training and testing sets. Unlike traditional machine learning techniques like support vector machines (SVM) and k-nearest neighbors (KNN) that often struggle with limited feature sets and lower accuracy, our proposed model overcomes these limitations. Notably, existing models applied to this dataset typically require manual feature selection and extraction, which can be time-consuming and less precise. In contrast, our model achieves superior results in binary classification by leveraging the advantages of LSTM and attention mechanisms. Through extensive experiments and evaluations with state-of-the-art ML/DL models, we demonstrate the effectiveness and superiority of our proposed approach. Our findings highlight the potential of combining LSTM and attention mechanisms for enhanced network intrusion detection.

Ransomware has evolved into a pervasive and extremely disruptive cybersecurity threat, causing substantial operational and financial damage to individuals and businesses. This article explores the critical domain of Ransomware detection and employs Machine Learning (ML) classifiers, particularly Decision Tree (DT), for Ransomware detection. The article also delves into the usefulness of DT in identifying Ransomware attacks, leveraging the innate ability of DT to recognize complex patterns within datasets. Instead of merely introducing DT as a detection method, we adopt a comprehensive approach, emphasizing the importance of fine-tuning DT hyperparameters. The optimization of these parameters is essential for maximizing the DT capability to identify Ransomware threats accurately. The obfuscated-MalMem2022 dataset, which is well-known for its extensive and challenging Ransomware-related data, was utilized to evaluate the effectiveness of DT in detecting Ransomware. The implementation uses the versatile Python programming language, renowned for its efficiency and adaptability in data analysis and ML tasks. Notably, the DT classifier consistently outperforms other classifiers in Ransomware detection, including K-Nearest Neighbors, Gradient Boosting Tree, Naive Bayes, and Linear Support Vector Classifier. For instance, the DT demonstrated exceptional effectiveness in distinguishing between Ransomware and benign data, as evidenced by its remarkable accuracy of 99.97%.

While many small and medium enterprises (SMEs)recognize the benefits of Big Data Analytics (BDA) for digital transformation, they face challenges in implementing this technology, highlighting the need for more research on its adoption by SMEs. The objective of this study is to amalgamate the Technology Organization Environment (TOE) framework with the Diffusion of Innovation (DOI) theory, aiming to dissect the factors that sway BDA adoption in Jordanian SMEs. Additionally, the study delves into how perceived usefulness impacts this adoption process. Utilizing structural equation modeling, the study examined data from 388 managers in Jordan. The study validates all its hypotheses, revealing that variables like relative advantage, compatibility, complexity, top management support, competitive pressure, and security influence perceived usefulness, which subsequently has a positive impact on BDA adoption. This research presents a range of theoretical and practical insights.

This study conducts a quantitative inquiry into how components of gamification and customization are being used in Saudi Arabia's educational system. In our investigation, we zero in on how these factors could contribute to skill development. This investigation uses a thorough and rigorous quantitative research approach to probe students' preferences for gamification components and their thoughts on customization. The findings highlight the amazing congruence between people's preference for gamification components like points and badges and the need for adaptation and feedback in optimizing the effectiveness of the educational process. Through careful component analysis, the current investigation successfully separates two distinct constructs: one highlights the importance of flexibility and responsiveness, while the other emphasizes the significance of pace and cultural appropriateness. The results of this research have important policy and practice implications for Saudi Arabia, where educational reforms are now underway. The goal of these changes is to boost academic performance by introducing student-specific, interactive gaming into the classroom.

AI is tanking different functions of businesses, and marketing is no exception. Digital marketing is gaining pace with the advancement in technology and the internet. The research aims to find the answer to the research question that marketers can benefit from AI in content creation for the digital market. The study also finds the relevance and use of AI in content creation and develops an AI infrastructure adoption model for content creators in digital marketing. The findings of this study were compiled using a systematic literature review that adhered to the Preferred Reporting Items for Systematic Reviews (PRISMA) statement and the criteria established by Meta-Analyses. The findings revealed that using AI in content creation provides personalized data, which helps the creators make relevant, targeted, and specific content. The research also finds that AI alone is not mature enough to carry out the whole content creation procedure as there is some limitation attached, especially regarding ethical implications. That’s why human surveillance of AI systems involved in content creation for the digital market is needed.

Adolescents increasingly turn to online sources for health information, raising concerns about the credibility of information and its impact on their behaviors. This study explores the factors shaping adolescents' online health information seeking (OHIS) behaviors. The study surveyed 381 adolescents to assess trust in online health information, eHealth literacy, parental behaviors, and AI-generated credibility scores. Structural Equation Modeling (SEM) was used to analyze data and test hypotheses based on the Social Cognitive Theory. Trust in online health information positively influenced disease-related OHIS behaviors (β = 0.24, p < 0.05) and fitness-related OHIS behaviors (β = 0.18, p < 0.05). Higher eHealth literacy correlated with increased disease-related OHIS behaviors (β = 0.32, p < 0.05) and fitness-related OHIS behaviors (β = 0.28, p < 0.05). Parental OHIS behaviors influenced adolescents' disease-related OHIS behaviors (β = 0.16, p < 0.05) and fitness-related OHIS behaviors (β = 0.22, p < 0.05). Parental OHIS mediation positively mediated these relationships (H7, H8). Higher AI-generated credibility scores associated with more disease-related OHIS behaviors (β = 0.20, p < 0.05) and fitness-related OHIS behaviors (β = 0.15, p < 0.05). Adolescents' eHealth literacy mediated these relationships (H11, H12). Trust, eHealth literacy, parental influence, and AI-generated credibility play vital roles in shaping adolescents' OHIS behaviors. Educators should prioritize enhancing eHealth literacy and promoting credible online sources to improve adolescents' health information seeking practices. This study contributes insights into the factors influencing adolescents' OHIS behaviors, emphasizing the role of parental mediation and AI-generated credibility scores. The findings inform the development of targeted health education interventions to encourage responsible online health information seeking among adolescents.

The growing significance of Artificial Intelligence (AI) across different fields highlights the essential role of user acceptance, as the success of this technology largely depends on its adoption and practical use by individuals. This research aims to examine how perceived cybersecurity, novelty value, and perceived trust affect students' willingness to accept AI in educational settings. The study's theoretical basis is the AI Device Use Acceptance (AIDUA) model. Using structural equation modeling, the study tested hypothesized relationships using data from 526 students at Jordanian universities. The results showed that social influence is positively associated with performance expectancy, while perceived cybersecurity is positively related to both performance and effort expectancy. Novelty value is positively associated with performance expectancy but a negative one with effort expectancy. Additionally, effort and performance expectancy significantly influence perceived trust and the willingness to accept AI. Moreover, perceived trust has a notable positive effect on the willingness to accept AI in education. These findings provide valuable guidance for the creation and improvement of AI-driven educational systems in universities, contributing to the broader understanding of AI technology acceptance in the educational field.