Search Results (98)

Social network platforms have a big impact on the development of companies by influencing clients’ behaviors and sentiments, which directly affect corporate reputations. Analyzing this feedback has become an essential component of business intelligence, supporting the improvement of long-term marketing strategies on a larger scale. The implementation of powerful sentiment analysis models requires a comprehensive and in-depth examination of each stage of the process. In this study, we present a new comparative approach for several feature extraction techniques, including TF-IDF, Word2Vec, FastText, and BERT embeddings. These methods are applied to three multilingual datasets collected from hotel review platforms in the tourism sector in English, French, and Arabic languages. Those datasets were preprocessed through cleaning, normalization, labeling, and balancing before being trained on various machine learning and deep learning algorithms. The effectiveness of each feature extraction method was evaluated using metrics such as accuracy, F1-score, precision, recall, ROC AUC curve, and a new metric that measures the execution time for generating word representations. Our extensive experiments demonstrate significant and excellent results, achieving accuracy rates of approximately 99% for the English dataset, 94% for the Arabic dataset, and 89% for the French dataset. These findings confirm the important impact of vectorization techniques on the performance of sentiment analysis models. They also highlight the important relationship between balanced datasets, effective feature extraction methods, and the choice of classification algorithms. So, this study aims to simplify the selection of feature extraction methods and appropriate classifiers for each language, thereby contributing to advancements in sentiment analysis. Full article

Rising population, combined with declining home food production, in Arab nations has resulted in increased food imports that intensifies their dependence on international markets for vital food supplies. These nations face challenges in achieving food security because crude oil price volatility creates difficulties in managing the expenses of imported food products. This research calculates the income and price elasticities of imported food demand to understand consumer behavior changes in response to income and price variations, which helps to explain their impact on regional food security. To our knowledge, this research presents the first analysis of imported food consumption patterns across Arab countries according to their income brackets. This study employs the static Almost Ideal Demand System model to examine food import data spanning from 1961 to 2020. The majority of imported food categories demonstrate inelastic price and income demand, which means that their essential food consumption remains stable despite cost fluctuations. The need for imports makes Arab nations vulnerable to external price changes, which endangers their food security. This research demonstrates why governments must implement policies through subsidies and taxation to reduce price volatility risks while ensuring food stability, which will lead to sustained food security for these nations. Full article

During the 28th Conference of the Parties (COP28), organized under the United Nations Framework Convention on Climate Change and hosted by the United Arab Emirates, member nations reached a global agreement to begin transitioning away from fossil fuel dependence, forcing the Gulf Cooperation Council (GCC) countries to balance their commitment to a green transition with the need to secure short-term energy supplies. This study highlights the challenges facing the GCC’s efforts to expand renewable energy, even as the region continues to have a significant influence over international energy markets. This study utilizes dynamic panel estimation over the period 2003 to 2022, focusing on the core pillars of the Energy Transition Index to analyze the evolving renewable energy use in the GCC. The results present a clear and optimistic perspective on the region’s renewable energy prospects. Despite the continued dependence on fossil fuels, the findings indicate that, if effectively managed, oil and gas revenues can serve as strategic instruments to support the transition toward cleaner energy sources. These insights offer policymakers robust guidance for long-term energy planning and highlight the critical importance of international collaboration in advancing the GCC’s sustainable energy transition. Full article

This study explores the factors influencing Arab tourists’ intention to revisit Turkish destinations, contributing to the theoretical discourse on tourist behavior, destination loyalty, and sustainable tourism development. Over the past decade, Türkiye (Turkey) has experienced a steady increase in tourists, with Arab visitors forming a significant segment. This growing market segment presents unique opportunities and challenges that remain understudied in academic literature. Despite their prominence, limited research exists on Arab tourists’ behavior, needs, and experiences in Türkiye. This study employs a mixed-method approach, combining surveys and interviews conducted between July and December 2024. Data from 713 surveys and 14 interviews were analyzed, revealing that 72% of Arab tourists were satisfied with their current visit, 49% with previous visits, 57% indicated a strong intention to revisit, and 81% recommended Turkish destinations to others. The study identifies seven key dimensions of revisit intention through Exploratory Factor Analysis that collectively explain 79.841% of the variance in revisit intention. The regression analysis demonstrates how different factors contribute to revisit decisions, with overall satisfaction (β = 0.622), loyalty (β = 0.521), financial status (β = 0.507), behavior of staff and locals (β = 0.484), cultural and social appeal (β = 0.478), overall experiences (β = 0.329), educational level (β = 0.333), accessibility and convenience (β = 0.288), service quality (β = 0.216), and length of stay (β = 0.128) emerging as significant predictors. These findings underscore the complexity of the decision-making process, suggesting that no single theory can fully explain tourists’ behavior and the sustainability of their visits. The study recommends further exploration of the proposed model and investments in tourism staff training, particularly in foreign languages, to enhance service quality and encourage repeat visits. Addressing issues such as unprofessional behavior and language barriers can improve overall satisfaction and loyalty, increasing the likelihood of Arab tourists revisiting Türkiye. This research highlights the importance of sustainable tourism practices in fostering long-term economic and social benefits for Turkish destinations. Full article

This study employs asymmetric quantile regression to investigate the asymmetric impact of WTI crude oil prices and economic policy uncertainty (EPU) on stock market returns from May 2014 to December 2024 in oil-importing (China, India, Germany, Italy, Japan, USA, and South Korea) and oil-exporting (Saudi Arabia, Russia, Iraq, Canada, and the United Arab Emirates) countries. The findings reveal that an increase in oil prices significantly impacts the returns of all countries. For oil-importing countries, an increase in oil prices consistently exhibits a positive impact, with insignificant effects in lower and medium quantiles and significant effects in higher quantiles. Conversely, a decrease in oil prices generally decreases stock market returns across all quantiles. This study offers valuable insights for investors to manage risks and improve the predictability of oil price fluctuations. It also provides strategies and policy implications for capitalists and decision-makers. By addressing contemporary issues and using up-to-date data, the study supports financial institutions and portfolio managers in formulating effective strategies. Full article

Agricultural festivals play a vital role in promoting sustainable farming, local economies, and cultural heritage. Understanding public sentiment toward these events can provide valuable insights to enhance event organization, marketing strategies, and economic sustainability. In this study, we collected and analyzed social media data from Twitter to evaluate public perceptions of Al-Baha’s agricultural festivals. Sentiment analysis was performed using both traditional machine learning and deep learning approaches. Specifically, six machine learning models including Multinomial Naïve Bayes (MNB), Support Vector Machine (SVM), Logistic Regression (LR), Random Forest (RF), k-Nearest Neighbors (KNN), and XGBoost (XGB) were compared against AraBERT, a transformer-based deep learning model. Each model was evaluated based on accuracy, precision, recall, and F1-score. The results demonstrated that AraBERT achieved the highest performance across all metrics, with an accuracy of 85%, confirming its superiority in Arabic sentiment classification. Among traditional models, SVM and RF performed best, whereas MNB and KNN struggled with sentiment detection. These findings highlight the role of sentiment analysis in supporting sustainable agricultural and tourism initiatives. The insights gained from sentiment trends can help festival organizers, policymakers, and agricultural stakeholders make data-driven decisions to enhance sustainable event planning, optimize resource allocation, and improve marketing strategies in line with the Sustainable Development Goals (SDGs). Full article

The Zaatari Camp in Jordan exemplifies how Syrian refugees transform a planned grid settlement into an organic urban environment through socio-spatial adaptation, reflecting their cultural identity and territorial practices. This study investigates the camp’s morphological evolution, analyzing how refugees reconfigure public and private spaces to prioritize privacy, security, and community cohesion. Using qualitative methods—including archival maps, photographs, and field observations—the research reveals how formal public areas are repurposed into private shelter extensions, creating zones of influence that mirror traditional Arab-Islamic urban patterns. Key elements such as mosques, markets, and hierarchical street networks emerge as cultural anchors, shaped by refugees’ prior urban experiences. However, this organic growth introduces challenges, such as blocked streets and undefined spaces, which hinder safety and service delivery, underscoring tensions between informal urbanization and structured planning. The findings advocate urban resilience and participatory planning frameworks that integrate socio-cultural values, emphasizing defensible boundaries, interdependence, and adaptable design. Refugees’ territorial behaviors—such as creating diagonal streets and expanding shelters—highlight their agency in reshaping urban systems, challenging conventional top-down approaches. This research focuses on land-use dynamics, sustainable cities, and adaptive urban systems in crisis contexts. By bridging gaps between displacement studies and urban theory, the study offers insights into fostering social inclusion and equitable infrastructure in transient settlements. Future research directions, including comparative analyses of refugee camps and cognitive mapping, aim to deepen understanding of socio-spatial resilience. Ultimately, this work contributes to global dialogues on informal urbanization and culturally responsive design, advocating for policies that align with the Sustainable Development Goals to rebuild cohesive, resilient urban environments in displacement settings. Full article

Against the backdrop of rapid growth in the food processing and biofuel industries across many countries, the global palm oil market has become a critical component of international agricultural trade. This study analyzes the evolution of the global palm oil trade network using palm oil trade data from 182 countries and identifies the associated influencing mechanisms to ensure the security of the international palm oil supply chain. The main findings are as follows: (1) over the past two decades, the global palm oil trade network has increasingly taken on a single, large-community structure, reflecting trends toward globalization and integration; however, it remains heavily concentrated around two core countries: Malaysia and Indonesia. (2) The degree of connectivity between countries in the global palm oil trade has steadily increased. While Malaysia and Indonesia continue to dominate the network, other communities have progressively shrunk in size. (3) In addition to Malaysia and Indonesia, countries such as the Netherlands, Germany, Italy, Singapore, and the United Arab Emirates (UAE) have become key players in the global palm oil trade network. (4) Quadratic assignment procedure (QAP) correlation and regression analyses show that differences in population, geographic distance, and institutional distance have significant and stable negative impacts on trade relationships, whereas the presence of a common language has a positive effect. Full article

This study investigates the occurrence, antimicrobial resistance (AMR) profiles, virulence factors, and plasmid composition of Enterococcus species isolated from salad ingredients in the United Arab Emirates (UAE). Four hundred salad vegetable items collected from local markets, over ten months through 2023, were screened, yielding an Enterococcus detection rate of 85.5% (342/400). E. casseliflavus was the most commonly identified species (50%), followed by E. faecium (20%) and E. faecalis (16%). Among 85 Enterococcus isolates tested for antimicrobial susceptibility, 55.3% displayed resistance to at least one agent, with 18.8% classified as multidrug-resistant (MDR). All isolates were not resistant to ampicillin, linezolid, teicoplanin, tigecycline, and high-level gentamicin. Intrinsic phenotypic resistance to vancomycin was found in E. gallinarum and E. casseliflavus, while low-level (<5%) ciprofloxacin and erythromycin resistance was sporadically detected in E. faecium and E. faecalis. Whole-genome sequencing (WGS) of 14 isolates (nine E. faecium, four E. faecalis, and one E. casseliflavus) unveiled a complex resistome. We report the first detection in salad vegetables of vancomycin resistance genes (vanC, vanXY-C2) in a vancomycin-susceptible E. faecalis isolate. Identifying tetM, ermB, and optrA genes in the studied isolates further underscored emerging resistance to tetracyclines, macrolides, and oxazolidinones. Concurrently, virulence gene analysis revealed 74 putative virulence factors, with E. faecalis harboring a higher diversity of biofilm-related and exoenzyme-encoding genes. One E. faecalis strain carried the cytolysin cluster (cylI, cylS, cylM), highlighting its pathogenic potential. Plasmid profiling identified 19 distinct plasmids, ranging from 3845 bp to 133,159 bp. Among the genome-sequenced isolates, mobilizable plasmids (47.3%) commonly carried AMR genes, especially tet(L) and tet(M), whereas conjugative plasmids (10.5%) did not harbor resistance determinants. These findings highlight that salad vegetables can still harbor and potentially transmit Enterococcus strains with clinically relevant resistance determinants and virulence traits. Enhancing foodborne AMR surveillance with WGS and targeted interventions is key to controlling its spread in the food. Full article

This study addresses the vast amount of information held by the banking sector, especially regarding opportunities in tourism development, production, and large residential projects. With advancements in information technology and databases, data mining has become essential for banks to optimally utilize available data. From January 2023 to July 2024, data from the Egyptian Arab Land Bank (EALB) were analyzed using data mining techniques, including rough set theory and the Weka version 3.0 program. The aim was to identify potential units for targeted marketing, improve customer satisfaction, and contribute to sustainable development goals. By integrating sustainability principles into financing approaches, this research promotes green banking, encouraging environmentally friendly and socially responsible investments. A survey of EALB customers assessed their interest in purchasing homes under the real estate financing program. The results were analyzed with GraphPad Prism version 9.0, with 95% confidence intervals and an R-squared value close to 1, and we identified 13 units (43% of the total units) as having the highest marketing potential. This study highlights data mining’s role in enhancing marketing for the EALB’s residential projects. Combining sustainable financing with data insights promotes green banking, aligning with customer preferences and boosting satisfaction and profitability. Full article

Author Gender Identification (AGI) is an extensively studied subject owing to its significance in several domains, such as security and marketing. Recognizing an author’s gender may assist marketers in segmenting consumers more effectively and crafting tailored content that aligns with a gender’s preferences. Also, in cybersecurity, identifying an author’s gender might aid in detecting phishing attempts where hackers could imitate individuals of a specific gender. Although studies in Arabic have mostly concentrated on written dialects, such as tweets, there is a paucity of studies addressing Modern Standard Arabic (MSA) in journalistic genres. To address the AGI issue, this work combines the beneficial properties of natural language processing with cutting-edge deep learning methods. Firstly, we propose a large 8k MSA article dataset composed of various columns sourced from news platforms, labeled with each author’s gender. Moreover, we extract and analyze textual features that may be beneficial in identifying gender-related cues through their writings, focusing on semantics and syntax linguistics. Furthermore, we probe several innovative deep learning models, namely, Convolutional Neural Networks (CNNs), LSTM, Bidirectional LSTM (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). Beyond that, a novel enhanced BERT model is proposed by incorporating gender-specific textual features. Through various experiments, the results underscore the potential of both BERT and the textual features, resulting in a 91% accuracy for the enhanced BERT model and a range of accuracy from 80% to 90% accuracy for deep learning models. We also employ these features for AGI in informal, dialectal text, with the enhanced BERT model reaching 68.7% accuracy. This demonstrates that these gender-specific textual features are conducive to AGI across MSA and dialectal texts. Full article

Patient satisfaction is a key measure of the quality of healthcare, directly impacting the success and competitiveness of healthcare providers in an increasingly demanding market. Traditional feedback collection methods often fall short of capturing the full spectrum of patient experiences, leading to skewed satisfaction reports due to patients’ reluctance to criticize services and the inherent limitations of survey designs. To address these issues, advanced Natural Language Processing (NLP) techniques such as aspect-based sentiment analysis are emerging as essential tools. Aspect-based sentiment analysis breaks down the feedback text into specific aspects and evaluates the sentiment for each aspect, offering a more nuanced and actionable understanding of patient opinions. Despite its potential, aspect-based sentiment analysis is under-explored in the healthcare sector, particularly in the Arabic literature. This study addresses this gap by performing an Arabic aspect-based sentiment analysis on patient experience data, introducing the newly constructed Hospital Experiences Arabic Reviews (HEAR) dataset, and conducting a comparative study using Bidirectional Embedding Representations from Transformers (BERT) combined with machine learning classifiers, as well as fine-tuning BERT models, including MARBERT, ArabicBERT, AraBERT, QARiB, and CAMeLBERT. Additionally, the performance of GPT-4 via OpenAI’s ChatGPT is evaluated in this context, making a significant contribution to the comparative study of BERT with traditional classifiers and the assessment of GPT-4 for aspect-based sentiment analysis in healthcare, ultimately offering valuable insights for enhancing patient experiences through the use of AI-driven approaches. The results show that the joint model leveraging MARBERT and SVM achieves the highest accuracy of 92.14%, surpassing other models, including GPT-4, in both aspect category detection and polarity tasks. Full article

Labneh is a popular fermented dairy product, which contemporarily has diversified into a varied range of styles, formulated with the inclusion of multiple additives, and is sourced across the globe. This has driven labneh’s emergence as a complex product with varying textural and rheological characteristics. The lack of scientific literature about labneh products available in the United Arab Emirates (UAE) market and their characterization has prompted this study. A detailed UAE market analysis of labneh for label, formulation, nutrition, and price variability was conducted. Surveyed labneh products were categorized as unpackaged, multinational company (MNC), small and medium enterprise (SME), and specialty products. They differed in manufacturing, such as acid ± enzyme coagulation with/without post-fermentation heat treatment, and contained various stabilizers, emulsifiers, preservatives, and processing aids. Interestingly, almost equal proportions, 64.7% and 67%, of MNC and SME labneh contained additives, respectively. All MNC labneh were post-heat-treated, in contrast to only 7% of SME labneh. Organic labneh and non-bovine milk-based labneh are not yet widely available. The second part of the study involved the physicochemical characterization of a select number of packaged labneh that were categorized in accordance with fat content as high-fat (17–18%), full-fat (7.1–8%), and lite-fat (3.5–4.5%). High-fat labneh showed a significantly higher complex viscosity, complex modulus, hardness, adhesiveness, stringiness, and fracturability, followed by lite-fat labneh compared to full-fat labneh, especially when it contained pectin. Full-fat labneh with added gums (and starch) and high-fat labneh with gums showed a significantly lower complex modulus compared to their respective control labneh. This study highlights the variety of commercial labneh products available and differences in their formulation, manufacturing, and composition, and provides specific dependencies of materials with their physicochemical characteristics. Full article

The Saudi government’s educational reforms aim to align the system with market needs and promote economic opportunities. However, a lack of credible data makes assessing public sentiment towards these reforms challenging. This research develops a sentiment analysis application to analyze public emotional reactions to educational reforms in Saudi Arabia using AraBERT, an Arabic language model. We constructed a unique Arabic dataset of 216,858 tweets related to the reforms, with 2000 manually labeled for public sentiment. To establish a robust evaluation framework, we employed random forests, support vector machines, and logistic regression as baseline models alongside AraBERT. We also compared the fine-tuned AraBERT Sentiment Classification model with CAMeLBERT, MARBERT, and LLM (GPT) models. The fine-tuned AraBERT model had an F1 score of 0.89, which was above the baseline models by 5% and demonstrated a 4% improvement compared to other pre-trained transformer models applied to this task. This highlights the advantage of transformer models specifically trained for the target language and domain (Arabic). Arabic-specific sentiment analysis models outperform multilingual models for this task. Overall, this study demonstrates the effectiveness of AraBERT in analyzing Arabic sentiment on social media. This approach has the potential to inform educational reform evaluation in Saudi Arabia and potentially other Arabic-speaking regions. Full article

This study aims to develop purple-coloured polymeric coatings using natural anthocyanin and desoxyanthocianidins (3-DXA) colourants for application to chocolate almonds. The objective is to achieve a stable and uniform colour formulation throughout processing and storage, enhancing the appearance and durability of the almonds to appeal to health-conscious consumers and align with market demands. Plant materials like sweet potato pulp, sweet potato peel, radish peel, black carrot, and sorghum were employed to obtain the desired purple hue. Anthocyanidins and 3-DXA were extracted from the matrices using solvent extraction and ultrasound-assisted methods at different pH values. High-performance liquid chromatography with diode array detection (HPLC-DAD) and high-resolution tandem mass spectrometry (HRMS/MS) were used to identify the compounds in the extracts. The highest antioxidant capacities, as measured by the DPPH^• and FRAP methods, were observed in purple sweet potato and dye factory extracts, respectively; meanwhile, sorghum extract inhibited both α-amylase and α-glucosidase, indicating its potential for managing postprandial hyperglycemia and type 2 diabetes. The degradation kinetics of coloured coatings in sugar syrup formulations with anthocyanins and 3-DXA revealed that locust bean gum offered the best colour stabilization for plant extracts, with sorghum extracts showing the highest and black carrot extracts the lowest colour variation when coated with Arabic gum. Sweet potato pulp extracts exhibited less colour variation in sugar pastes, both with and without blue spirulina dye, compared to factory dye, highlighting their potential as a more stable and suitable alternative for colouring purple almonds, particularly over a five-month storage period. This study supports sustainable practices in the confectionery industry while aligning with consumer preferences for healthier and environmentally friendly products. Full article