Riyadh Mehdi

Student attrition, a crucial factor in determining institutions’ financial resources, is also a measure of an institution’s academic standing, with a direct impact on its revenue. This study, which examined the factors influencing students’ departure from the Information Systems (IS) program, has significant implications for higher education. The research was conducted in 2 stages. Initially, we experimented with 13 machine learning algorithms to identify the most accurate method for predicting student attrition. Our findings revealed that Extra Trees, Light Gradient Boosting Machine, and Random Forests are the top 3 predictors in that order. In the second stage, we used these algorithms to identify the most influential factors driving student attrition. Our results indicated that the 3 classifiers identified the Last Grade Point Average (Last GPA) as the most significant factor affecting students’ decision to leave the IS program. Performance in mathematics and gender are the other 2 factors affecting dropout. We have found that, as a percentage, more male than female students are leaving the program. Moreover, female students are primarily transferring to more academically demanding majors, such as data analytics and information technology, while male students are transferring to less technology-oriented majors, such as management and law. This finding is reinforced by the observation that female students’ mathematics performance among students leaving the IS program is significantly higher than that of male students. Our results can have significant policy implications for admission procedures and academic advising, positively affecting the IS program’s attrition rate.

Predicting undergraduate university students' poor academic performance is crucial for reducing its adverse effects on their mental health, enhancing students’ ability to cope with stressful situations, and thereby reducing the harm it causes to their overall well-being. This study examines the factors contributing to poor performance among freshmen students in the Information Systems program, leading to the development of stressful behavior and eventual program dropout. Factors such as students’ gender, nationality, high school type, high school score, English level, performance in mathematics, performance in programming, and grade point average, among others, were investigated using three machine learning algorithms: Extra Trees, Light Gradient Boosting Machine, and Random Forests. The results indicated that the grade point average is the most significant factor affecting students’ mental health, resulting in their leaving the program. Performance in mathematics and gender are the other factors affecting students’ stress behavior. After investigations, our results found that among students who performed poorly, males left the information systems program more than their female counterparts. They mainly transferred to less technology-oriented majors, such as management and law. In addition, it was found that women performed better in mathematics among students leaving the program than men. These results can be a central priority for educators, policymakers, and community members to positively affect students' academic performance and mental health.

This article presents a comprehensive analysis of the global discourse on the hijab on Instagram, a key platform for cultural and fashion expressions. Employing a mixed-methods approach, it examines a dataset of 100,000 Instagram posts to explore representations and discussions of the hijab in online communities. The study includes temporal analysis of discourse evolution, text classification of narratives using advanced natural language processing (NLP) techniques like topic modelling and sentiment analysis, and network analysis of community interactions. Key findings reveal the multifaceted nature of the hijab discourse, encompassing themes of fashion, religion and community. The temporal analysis uncovers peaks in hijab-related posts from October 2021 onwards and between May and July 2022, coinciding with Islamic events and the rise of modest fashion. Sentiment analysis indicates a generally positive and neutral perception of the hijab, while emotion analysis highlights joy, anticipation and trust as dominant emotions. Text classification identifies five main topics: hijab styles and fashion, sizing and shipping, colours and product types, religion and spirituality, and product orders. Network analysis visualizes the interconnected nature of these themes and communities. The study makes original contributions by shedding light on the ‘hijabista’ phenomenon, representing Muslim women who blend fashion with modesty on Instagram, and by demonstrating Instagram’s role in shaping contemporary hijab discourse related to identity, empowerment and cultural representation. The findings enhance understanding of social media’s impact on cultural discourses and offer valuable insights into the social and cultural implications of these online narratives for scholars, businesses and policy-makers.

This study aims to rate the impact of the three major risks (credit, capital adequacy, and liquidity) on three financial performance measures (return on equity (ROE), earnings per share (EPS), and price-earnings ratio (PER)). This study stands out as one of the few in its field, and the only one focusing on banks in the Middle East and Africa, to employ the adaptive neural network-based fuzzy inference system (ANFIS) that combines neural networks and fuzzy logic systems. The significance of this study lies in its comprehensive coverage of major risks and performance variables and its application of highly technical, sophisticated, and precise AI techniques (ANFIS). The main findings indicate that credit risk, as measured by the non-performing loans (NPL) has significant impact on both ROE and EPS. Liquidity risk comes second in importance for ROE and EPS, with the loan-deposit ratio (LDR) being the dominant component. In contrast, liquidity risk is the most significant determinant of PER, followed by capital adequacy. Our results also show that CAR, LDR, and NPL are the most significant risk components of capital adequacy, liquidity, and credit risks, respectively. The study contributes to business knowledge by applying the ANFIS technique as an accurate predictor of risk rating. Future research will explore the relationship between risks and macroeconomic indicators and differences among countries.

Banking risk measurement and management remain one of many challenges for managers and policymakers. This study contributes to the banking literature and practice in two ways by (a) proposing a risk ranking index based on the Mahalanobis Distance (MD) between a multidimensional point representing a bank’s risk measures and the corresponding critical ratios set by the banking authorities and (b) determining the relative importance of a bank’s risk ratios in affecting its financial standing using an Adaptive Neuro-Fuzzy Inference System. In this study, ten financial ratios representing five risk areas were considered, namely: Capital Adequacy, Credit, Liquidity, Earning Quality, and Operational risk. Data from 45 Gulf banks for the period 2016–2020 was used to develop the model. Our findings indicate that a bank is in a sound risk position at the 99%, 95%, and 90% confidence level if its Mahalanobis distance exceeds 4.82, 4.28, and 4.0, respectively. The maximum distance computed for the banks in this study was 9.31; only five out of the forty-five banks were below the 4.82 and one below the 4.28 and 4.0 thresholds at 3.96. Sensitivity analysis of the risks indicated that the Net Interest Margin is the most significant factor in explaining variations in a bank’s risk position, followed by Capital Adequacy Ratio, Common Equity Tier1, and Tier1 Equity in order. The remaining financial ratios: Non-Performing Loans, Equity Leverage, Cost Income Ratio, Loans to Total Assets, and Loans to Deposits have the least influence in the order given; the Provisional Loans Ratio appears to have no influence.

Predicting students’ academic performance and the factors that significantly influence it can improve students’ completion and graduation rates, as well as reduce attrition rates. In this study, we examine the factors influencing student academic achievement. A fuzzy-neural approach is adopted to build a model that predicts and explains variations in course grades among students, based on course category, student course attendance rate, gender, high-school grade, school type, grade point average (GPA), and course delivery mode as input predictors. The neuro-fuzzy system was used because of its ability to implicitly capture the functional form between the dependent variable and input predictors. Our results indicate that the most significant predictors of course grades are student GPA, followed by course category. Using sensitivity analysis, student attendance was determined to be the most significant factor explaining the variations in course grades, followed by GPA, with course delivery mode ranked third. Our findings also indicate that a hybrid course delivery mode has positively impacted course grades as opposed to online or face-to-face course delivery alone.

Predicting student’s successful completion of academic programs and the features that influence their performance can have a significant effect on improving students’ completion, and graduation rates and reduce attrition rates. Therefore, identifying students are at risk, and the courses where improvements in content, delivery mode, pedagogy, and assessment activities can improve students’ learning experience and completion rates. In this work, we have developed a prediction and explanatory model using adaptive neuro-fuzzy inference system (ANFIS) methodology to predict the grade point average (GPA), at graduation time, of students enrolled in the information technology program at Ajman University. The approach adopted uses students’ grades in introductory and fundamental IT courses and high school grade point average (HSGPA) as predictors. Sensitivity analysis was performed on the model to quantify the relative significance of each predictor in explaining variations in graduation GPA. Our findings indicate HSGPA is the most influential factor in predicting graduation GPA, with data structures, operating systems, and software engineering coming closely in second place. On the explanatory side, we have found that discrete mathematics was the most influential course causing variations in graduation GPA, followed by software engineering, information security, and HSGPA. When we ran the model on the testing data, 77% of the predicted values fell within one root mean square error (0.29) of the actual GPA, which has a maximum of four. We have also shown that the ANFIS approach has better predictive accuracy than commonly used techniques such as multilinear regression. We recommend that IT programs at other institutions conduct comparable studies and shed some light on our findings.

The COVID-19 pandemic introduced unprecedented challenges for people and governments. Vaccines are an available solution to this pandemic. Recipients of the vaccines are of different ages, gender, and religion. Muslims follow specific Islamic guidelines that prohibit them from taking a vaccine with certain ingredients. This study aims at analyzing Facebook and Twitter data to understand the discourse related to halal vaccines using aspect-based sentiment analysis and text emotion analysis. We searched for the term “halal vaccine” and limited the timeline to the period between 1 January 2020, and 30 April 2021, and collected 6037 tweets and 3918 Facebook posts. We performed data preprocessing on tweets and Facebook posts and built the Latent Dirichlet Allocation (LDA) model to identify topics. Calculating the sentiment analysis for each topic was the next step. Finally, this study further investigates emotions in the data using the National Research Council of Canada Emotion Lexicon. Our analysis identified four topics in each of the Twitter dataset and Facebook dataset. Two topics of “COVID-19 vaccine” and “halal vaccine” are shared between the two datasets. The other two topics in tweets are “halal certificate” and “must halal”, while “sinovac vaccine” and “ulema council” are two other topics in the Facebook dataset. The sentiment analysis shows that the sentiment toward halal vaccine is mostly neutral in Twitter data, whereas it is positive in Facebook data. The emotion analysis indicates that trust is the most present emotion among the top three emotions in both datasets, followed by anticipation and fear.