This paper examines speakers’ systematic errors while speaking English as a foreign language (EFL) among students in Arab countries with the purpose of automatically recognizing and correcting mispronunciations using speech recognition, phonological features, and machine learning. Accordingly, three main steps are implemented towards this purpose: identifying the most frequently wrongly pronounced phonemes by Arab students, analyzing the systematic errors these students make in doing so, and developing a framework that can aid the detection and correction of these pronunciation errors. The proposed automatic detection and correction framework used the collected and labeled data to construct a customized acoustic model to identify and correct incorrect phonemes. Based on the trained data, the language model is then used to recognize the words. The final step includes construction samples of both correct and incorrect pronunciation in the phonemes model and then using machine learning to identify and correct the errors. The results showed that one of the main causes of such errors was the confusion that leads to wrongly utilizing a given sound in place of another. The automatic framework identified and corrected 98.2% of the errors committed by the students using a decision tree classifier. The decision tree classifier achieved the best recognition results compared to the five classifiers used for this purpose.

The use of data mining to predict early employment readiness of students is gaining importance due to the expansion of data production in various industries. This study aims to address the employability issue in Middle Eastern nations by utilizing an Adaptive Neuro-Fuzzy Inference System (ANFIS) data mining technology. The experimental investigation used data from tracer studies conducted by three Jordanian universities, consisting of 22 parameters. Results showed that despite achieving an accuracy of 94% for the graduate dataset, ANFIS exhibited high complexity due to the large number of attributes used. The study has implications for selecting relevant variables and investigating multiple aspects. Data mining has various applications, including classification, clustering, regression, association rule development, and outlier analysis. As data production continues to expand, this study provides insights into the potential use of ANFIS in predicting early employment readiness of students in Middle Eastern nations.

The expression "social media" refers to a software-based platform developed for users’ benefit. People use it to gain social power, market their products, conduct online business, and share information and ideas. This digital ecosystem has become helpful in various ways, but research indicates that it does not come for free. Addiction, depression, and anxiety are some of the adverse conditions discussed in many studies. The purpose of this study is to mark if there is a relationship between using social media networks and the numbering of people with anxiety or depression. Also, by addressing the need to learn more about what makes people use social networks and how that use affects anxiety and depression in Arabic-speaking users in Jordan, we can help people from different cultures understand each other better. This research uses TAM, telepresence, and survey data from 1050 people, mainly from Jordan. The research looks at how the usage of social media is related to supposed usefulness, supposed ease of use, trust, social influence, age, gender, level of education, marital status, the time spent on the internet, preferred social media network, and perceived usefulness of SNS. AMOS 20 methods of confirmatory factor analysis (CFA), structural equation modeling (SEM), and machine learning (ML), such as SMO, ANN, random forest, and the bagging reduced error pruning tree (RepTree), were used to test the proposed model hypotheses. According to the results, the researchers found high correlations between social network usage and depression and anxiety. The use of social networking sites is also affected by how useful they are seen to be, how easy they are to use, trust, social influence, and telepresence. Also, the moderator's age, gender, level of education, marital status, amount of time spent on the internet, experience with the internet, and favorite social networks all affect how they plan to use social networks.

Phishing is an attack by cybercriminals to obtain sensitive information such as account IDs, usernames, and passwords through the use of the anonymous structure of the Internet. Although software companies are launching new anti-phishing tools that use blacklists, heuristics, visual methods, and machine learning-based methods, these products cannot prevent all phishing attacks. This research offers an opportunity to increase accuracy in the detection of phishing sites. This study develops a model using machine learning algorithms, specifically the decision tree and the random forest, due to their outperforming the rest of the classifiers and being accredited by researchers in this field to achieve the highest accuracy. The study is based on two phases: the first phase is to measure the accuracy of classifiers on the dataset in the usual way before and after feature selection. The second phase uses the class decomposition approach and measures the accuracy of classifiers in the dataset before feature selection and after feature selection to detect phishing sites. The class decomposition approach is a technique to improve the performance of classifiers by distributing each class into clusters and renaming the examples of each cluster with a new class. This provides a specific metric that more accurately predicts the level of phishing. Testing on a dataset containing 11,055 instances, 4,898 phishing, and 6,157 legitimate, each instance has 30 features. It achieved the highest accuracy in the first phase through the random forest algorithm by 96.9% before feature selection, and after feature selection, it was by 97.1%. In the second phase, the highest accuracy of both the decision tree and random forest classifiers was achieved by 100% with the two and four classes after feature selection. While before feature selection, the random forest algorithm achieved 100% with only the two classes.

Supply chain disruptions pose significant challenges to global economic stability, necessitating advanced predictive tools for effective risk management. As Machine Learning (ML) offers promising solutions for enhancing resiliency, this study investigates its applications in supply chain management. Utilizing a systematic literature review, we examined recent research to identify effective ML models and techniques, focusing on both supervised and unsupervised learning. Our analysis covered various industries to understand the adaptability and effectiveness of these models in mitigating supply chain risks. The results highlight the growing implementation of ML in anticipating disruptions, with supervised learning demonstrating superior predictive precision under specific conditions. At the same time, unsupervised approaches offer valuable insights in data-scarce scenarios. Context-specific data surfaced as crucial in model accuracy, underscoring the need for tailored approaches. This study concludes that integrating ML with current supply chain systems can significantly enhance operational resilience, advocating for continued exploration of novel data sources and interdisciplinary collaborative efforts.

Nomophobia is a term describing a growing fear in today’s world, the fear of being without a mobile device or beyond mobile phone contact. It is the biggest non-drug addiction of the 21st century and is mainly affected by teen-aged students. Those experiencing nomophobia may feel a sense of panic, anxiety, or distress when they are separated from their mobile phones. This work uses different statistical tools to identify the risk factor of nomophobia and machine learning techniques to propose a fresh way to measure and understand nomophobia. To create a predictive model for nomophobia, we gathered information from a broad sample (n = 357) of smartphone users and used a variety of machine learning methods. Using a questionnaire on 17 different factors and performing a statistically significant test (p<0.05) and ordinal logistic regression analysis on respondents age, level of education, CGPA, self-evaluation, per-day mobile phone usage, and use of media, we can recognize the most important features causative of nomophobia. The context of maximum phone usage is an important feature that highly affects nomophobia. About 201 respondents are at a moderate level. To develop a predictive model, decision tree (DT), random forest (RF), Gaussian Naïve Bayes (NB), and support vector machine (SVM) are utilized in this study for recognition of nomophobia addiction. Proposing an ensemble method to refine the predictive performance. From the analysis, we have found that the SVM feature selector with ensemble algorithm has classified the extent of smartphone addiction with a 57% accuracy rate. Our findings show that nomophobia tendencies can be accurately captured and predicted by machine learning approaches. The model distinguished between students who had symptoms of nomophobia and those who did not with remarkable accuracy. This study of machine learning-based methods presents a viable tool for diagnosing and treating nomophobia in students, eventually assisting in the creation of focused interventions and preventive measures.