Search Results (66)

Legal judgment prediction is an emerging application of artificial intelligence in the legal domain, offering significant potential to enhance legal decision support systems. Such systems can improve judicial efficiency, reduce burdens on legal professionals, and assist in early-stage case assessment. This study focused on predicting whether a legal case would be Accepted or Rejected using only the Fact section of court rulings. A key challenge lay in processing long legal documents, which often exceeded the input length limitations of transformer-based models. To address this, we proposed a two-step methodology: first, each document was segmented into sentence-level inputs compatible with AraBERT—a pretrained Arabic transformer model—to generate sentence-level predictions; second, these predictions were aggregated to produce a document-level decision using several methods, including Mean, Max, Confidence-Weighted, and Positional aggregation. We evaluated the approach on a dataset of 19,822 real-world cases collected from the Saudi Arabian Commercial Court. Among all aggregation methods, the Confidence-Weighted method applied to the AraBERT-based classifier achieved the highest performance, with an overall accuracy of 85.62%. The results demonstrated that combining sentence-level modeling with effective aggregation methods provides a scalable and accurate solution for Arabic legal judgment prediction, enabling full-length document processing without truncation. Full article

In this work, we propose a knowledge-aware approach for Arabic automatic question generation (QG) that leverages the multilingual T5 (mT5) transformer augmented with a pre-trained Arabic question-answering model to address challenges posed by Arabic’s morphological richness and limited QG resources. Our system generates both subjective questions and multiple-choice questions (MCQs) with contextually relevant distractors through a dual-model pipeline that tailors the decoding strategy to each subtask: the question generator employs beam search to maximize semantic fidelity and lexical precision, while the distractor generator uses top-k sampling to enhance diversity and contextual plausibility. The QG model is fine-tuned on Arabic SQuAD, and the distractor model is trained on a curated combination of ARCD and Qudrat. Experimental results show that beam search significantly outperforms top-k sampling for fact-based question generation, achieving a BLEU-4 score of 27.49 and a METEOR score of 25.18, surpassing fine-tuned AraT5 and translated English–Arabic baselines. In contrast, top-k sampling is more effective for distractor generation, yielding higher BLEU scores and producing distractors that are more diverse yet remain pedagogically valid, with a BLEU-1 score of 20.28 establishing a strong baseline in the absence of prior Arabic benchmarks. Human evaluation further confirms the quality of the generated questions. This work advances Arabic QG by providing a scalable, knowledge-aware solution with applications in educational technology, while demonstrating the critical role of task-specific decoding strategies and setting a foundation for future research in automated assessment. Full article

The recent increase in extremist material on social media platforms makes serious countermeasures to international cybersecurity and national security efforts more difficult. RADAR#, a deep ensemble approach for the detection of radicalization in Arabic tweets, is introduced in this paper. Our model combines a hybrid CNN-Bi-LSTM framework with a top Arabic transformer model (AraBERT) through a weighted ensemble strategy. We employ domain-specific Arabic tweet pre-processing techniques and a custom attention layer to better focus on radicalization indicators. Experiments over a 89,816 Arabic tweet dataset indicate that RADAR# reaches 98% accuracy and a 97% F1-score, surpassing advanced approaches. The ensemble strategy is particularly beneficial in handling dialectical variations and context-sensitive words common in Arabic social media updates. We provide a full performance analysis of the model, including ablation studies and attention visualization for better interpretability. Our contribution is useful to the cybersecurity community through an effective early detection mechanism of online radicalization in Arabic language content, which can be potentially applied in counter-terrorism and online content moderation. Full article

To address the underutilization of Schizochytrium limacinum meal, polysaccharides from Schizochytrium limacinum meal (SLMPs) were prepared via ultrasonic-assisted eutectic-solvent-based extraction. Although polysaccharides exhibit promising application potential, the structural ambiguity of SLMPs necessitates systematic investigation to elucidate their structure–activity relationships, thereby providing a scientific foundation for their subsequent development and utilization. Using response-surface methodology (RSM), the optimized extraction conditions were determined as follows: ultrasonic temperature of 52 °C, ultrasonic duration of 31 min, ultrasonic power of 57 W, water content of 29%, and a material-to-liquid ratio of 1:36 g/mL. Under these conditions, the maximum polysaccharide yield reached 9.25%, demonstrating a significant advantage over the conventional water extraction method (4.18% yield). Following purification, the antioxidant activity and structural characteristics of SLMPs were analyzed. The molecular weight, monosaccharide composition, reducing groups, and higher-order conformation were systematically correlated with antioxidant activity. Fourier-transform infrared spectroscopy (FTIR), monosaccharide composition analysis, and ¹H nuclear magnetic resonance (NMR) spectroscopy revealed characteristic polysaccharide functional groups (C–O, O–H, and C=O). Monosaccharides such as glucose (Glc), galactose (Gal), and arabinose (Ara) were found to enhance antioxidant activity. High-performance gel permeation chromatography (HPGPC) indicated a molecular weight of 20.7 kDa for SLMPs, with low-molecular-weight fractions exhibiting superior antioxidant activity. Scanning electron microscopy (SEM) further demonstrated that ultrasonically extracted polysaccharides possess porous structures capable of chelating redox-active functional groups. These findings suggest that ultrasonic-assisted eutectic-solvent-based extraction is an efficient method for polysaccharide extraction while preserving antioxidant properties. Full article

To investigate the rheological properties and influence mechanisms of twin-screw activated rubber composite-modified asphalt, we used SBS-modified asphalt (SBS) as the reference. Raw rubber powder composite-modified asphalt (RA/SBS) and activated rubber composite-modified asphalt (ARA/SBS) were prepared. A dynamic shear rheometer (DSR) and bending beam rheometer (BBR) were employed to comparatively analyze the rheological characteristics of the three modified asphalts, while Fourier transform infrared spectroscopy (FTIR) and fluorescence microscopy were used to reveal the micro-mechanisms in ARA/SBS. The results showed that ARA/SBS exhibited better storage stability and low-temperature flexibility compared to SBS and RA/SBS, and ARA/SBS demonstrated lower viscosity than RA/SBS. Among the three, ARA/SBS showed significantly improved high-temperature performance. The comparison of creep stiffness S and creep rate m indicated optimal performance in ARA/SBS, confirming that twin-screw activated rubber powder could significantly enhance the low-temperature properties of modified asphalt. Microscopically, chemical reactions occurred between oxygen-containing functional groups in activated rubber and polar groups in asphalt, while a cross-linked network structure formed between activated rubber molecules and asphalt molecular chains, improving compatibility and enhancing the rheological properties of composite modified asphalt. Full article

Azelaic acid (AZA), an aliphatic dicarboxylic acid (HOOC-(CH2)₇-COOH), is widely used in dermatology. It functions as an inhibitor of tyrosinase, mitochondrial respiratory chain enzymes, and DNA synthesis, while also scavenging free radicals and reducing reactive oxygen species (ROS) production by neutrophils. AZA has demonstrated anti-proliferative and cytotoxic effects on various cancer cells. However, its therapeutic potential in acute myeloid leukemia (AML) remains largely unexplored. AML is a complex hematologic malignancy characterized by the clonal transformation of hematopoietic precursor cells, involving chromosomal rearrangements and multiple gene mutations. The disease is associated with poor prognosis and high relapse rates, primarily due to its propensity to develop resistance to treatment. Recent studies indicate that AZA suppresses AML cell proliferation by inducing apoptosis and arresting the cell cycle at the G1 phase, with minimal cytotoxic effects on healthy cells. Additionally, AZA exerts antileukemic activity by modulating the ROS signaling pathway, enhancing the total antioxidant capacity in both AML cell lines and patient-derived cells. AZA also sensitizes AML cells to Ara-C chemotherapy. In vivo, AZA has been shown to reduce leukemic spleen infiltration and extend survival. As our understanding of AML biology progresses, the development of new molecularly targeted agents, in combination with traditional chemotherapy, offers the potential for improved treatment outcomes. This review aims to provide a comprehensive synthesis of preclinical evidence on the therapeutic potential of AZA in AML, consolidating current knowledge and identifying future directions for its clinical application. Full article

Arabic poetry follows intricate rhythmic patterns known as ‘arūḍ’ (prosody), which makes its automated categorization particularly challenging. While earlier studies primarily relied on conventional machine learning and recurrent neural networks, this work evaluates the effectiveness of transformer-based models—an area not extensively explored for this task. We investigate several pretrained transformer models, including Arabic Bidirectional Encoder Representations from Transformers (Arabic-BERT), BERT base Arabic (AraBERT), Arabic Efficiently Learning an Encoder that Classifies Token Replacements Accurately (AraELECTRA), Computational Approaches to Modeling Arabic BERT (CAMeLBERT), Multi-dialect Arabic BERT (MARBERT), and Modern Arabic BERT (ARBERT), alongside deep learning models such as Bidirectional Long Short-Term Memory (BiLSTM) and Bidirectional Gated Recurrent Units (BiGRU). This study uses half-verse data across 14 m. The CAMeLBERT model achieved the highest performance, with an accuracy of 90.62% and an F1-score of 0.91, outperforming other models. We further analyze feature significance and model behavior using the Local Interpretable Model-Agnostic Explanations (LIME) interpretability technique. The LIME-based analysis highlights key linguistic features that most influence model predictions. These findings demonstrate the strengths and limitations of each method and pave the way for further advancements in Arabic poetry analysis using deep learning. 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

Mental health disorders represent a substantial global health concern, impacting millions and placing a significant burden on public health systems. Natural Language Processing (NLP) has emerged as a promising tool for analyzing large textual datasets to identify and predict mental health challenges. The aim of this scoping review is to identify the Arabic NLP techniques employed in mental health research, the specific mental health conditions addressed, and the effectiveness of these techniques in detecting and predicting such conditions. This scoping review was conducted according to the PRISMA-ScR (Preferred Reporting Items for Systematic reviews and Meta-Analyses extension for Scoping Reviews) framework. Studies were included if they focused on the application of NLP techniques, addressed mental health issues (e.g., depression, anxiety, suicidal ideation) within Arabic text data, were published in peer-reviewed journals or conference proceedings, and were written in English or Arabic. The relevant literature was identified through a systematic search of four databases: PubMed, ScienceDirect, IEEE Xplore, and Google Scholar. The results of the included studies revealed a variety of NLP techniques used to address specific mental health issues among Arabic-speaking populations. Commonly utilized techniques included Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), Recurrent Neural Network (RNN), and advanced transformer-based models such as AraBERT and MARBERT. The studies predominantly focused on detecting and predicting symptoms of depression and suicidality from Arabic social media data. The effectiveness of these techniques varied, with trans-former-based models like AraBERT and MARBERT demonstrating superior performance, achieving accuracy rates of up to 99.3% and 98.3%, respectively. Traditional machine learning models and RNNs also showed promise but generally lagged in accuracy and depth of insight compared to transformer models. This scoping review highlights the significant potential of NLP techniques, particularly advanced transformer-based models, in addressing mental health issues among Arabic-speaking populations. Ongoing research is essential to keep pace with the rapidly evolving field and to validate current findings. Full article

Paraphrasing means expressing the semantic meaning of a text using different words. Paraphrasing has a significant impact on numerous Natural Language Processing (NLP) applications, such as Machine Translation (MT) and Question Answering (QA). Machine Learning (ML) methods are frequently employed to generate new paraphrased text, and the generative method is commonly used for text generation. Generative Pre-trained Transformer (GPT) models have demonstrated effectiveness in various text generation tasks, including summarization, proofreading, and rephrasing of English texts. However, GPT-4’s capabilities in Arabic paraphrase generation have not been extensively studied despite Arabic being one of the most widely spoken languages. In this paper, the researchers evaluate the capabilities of GPT-4 in text paraphrasing for Arabic. Furthermore, the paper presents a comprehensive evaluation method for paraphrase quality and developing a detailed framework for evaluation. The framework comprises Bilingual Evaluation Understudy (BLEU), Recall-Oriented Understudy for Gisting Evaluation (ROUGE), Lexical Diversity (LD), Jaccard similarity, and word embedding using the Arabic Bi-directional Encoder Representation from Transformers (AraBERT) model with cosine and Euclidean similarity. This paper illustrates that GPT-4 can effectively produce a new paraphrased sentence that is semantically equivalent to the original sentence, and the quality framework efficiently ranks paraphrased pairs according to quality criteria. Full article

Social media is crucial for gathering public feedback on government services, particularly in the traffic sector. While Aspect-Based Sentiment Analysis (ABSA) offers a means to extract actionable insights from user posts, analyzing Arabic content poses unique challenges. Existing Arabic ABSA approaches heavily rely on supervised learning and manual annotation, limiting scalability. To tackle these challenges, we suggest an integrated framework combining unsupervised BERTopic-based Aspect Category Detection with distance supervision using a fine-tuned CAMeLBERT model for sentiment classification. This is further complemented by transformer-based summarization through a fine-tuned AraBART model. Key contributions of this paper include: (1) the first comprehensive Arabic traffic services dataset containing 461,844 tweets, enabling future research in this previously unexplored domain; (2) a novel unsupervised approach for Arabic ABSA that eliminates the need for large-scale manual annotation, using FastText custom embeddings and BERTopic to achieve superior topic clustering; (3) a pioneering integration of aspect detection, sentiment analysis, and abstractive summarization that provides a complete pipeline for analyzing Arabic traffic service feedback; (4) state-of-the-art performance metrics across all tasks, achieving 92% accuracy in ABSA and a ROUGE-L score of 0.79 for summarization, establishing new benchmarks for Arabic NLP in the traffic domain. The framework significantly enhances smart city traffic management by enabling automated processing of citizen feedback, supporting data-driven decision-making, and allowing authorities to monitor public sentiment, identify emerging issues, and allocate resources based on citizen needs, ultimately improving urban mobility and service responsiveness. Full article

Road traffic accidents (RTAs) are a significant public health and safety concern, resulting in numerous injuries and fatalities. The growing number of cases referred to traffic accident rooms in courts has underscored the necessity for an automated solution to determine victim indemnifications, particularly given the limited number of specialized judges and the complexity of cases involving multiple victims. This paper introduces RTACompensator, an artificial intelligence (AI)-driven decision support system designed to automate indemnification calculations for road accident victims. The system comprises two main components: a calculation module that determines initial compensation based on factors such as age, salary, and medical assessments, and a machine learning (ML) model that assigns liability based on police accident reports. The model uses Arabic bidirectional encoder representations from transformer (AraBERT) embeddings to generate contextual vectors from the report, which are then processed by extreme gradient boosting (XGBoost) to determine responsibility. The model was trained on a purpose-built Arabic corpus derived from real-world legal judgments. To expand the dataset, two data augmentation techniques were employed: multilingual bidirectional encoder representations from transformers (BERT) and Gemini, developed by Google DeepMind. Experimental results demonstrate the model’s effectiveness, achieving accuracy scores of 97% for the BERT-augmented corpus and 97.3% for the Gemini-augmented corpus. These results underscore the system’s potential to improve decision-making in road accident indemnifications. Additionally, the constructed corpus provides a valuable resource for further research in this domain, laying the groundwork for future advancements in automating and refining the indemnification process. Full article

Understanding public sentiment on health and fitness is essential for addressing regional health challenges in Saudi Arabia. This research employs sentiment analysis to assess fitness awareness by analyzing content from the X platform (formerly Twitter), using a dataset called Saudi Aware, which includes 3593 posts related to fitness awareness. Preprocessing steps such as normalization, stop-word removal, and tokenization ensured high-quality data. The findings revealed that positive sentiments about fitness and health were more prevalent than negative ones, with posts across all sentiment categories being most common in the western region. However, the eastern region exhibited the highest percentage of positive sentiment, indicating a strong interest in fitness and health. For sentiment classification, we fine-tuned two transformer architectures—BERT and GPT—utilizing three BERT-based models (AraBERT, MARBERT, CAMeLBERT) and GPT-3.5. These findings provide valuable insights into Saudi Arabian attitudes toward fitness and health, offering actionable information for public health campaigns and initiatives. Full article

Esterified ARA on the inner surface of the cell membrane is hydrolyzed to its free form by phospholipase A2 (PLA2), which is further metabolized by COXs and lipoxygenases (LOXs) and cytochrome P450 (CYP) enzymes. PGs produce detrimental effects due to their proinflammatory properties. The generation of prostaglandin (PG)G₂ and PGH₂ is triggered by cyclooxygenase (COX) isozymes such as COX-1 and COX-2. Prostaglandin E2 (PGE2) is significantly elevated in ASD. Considerable data indicate that COX enzymes and their metabolites of ARA play important roles in the initiation and development of human neurodevelopmental diseases. The involvement of disrupted COX2/PGE2 signaling in ASD pathology in changing neuronal cell behavior and the expression of ASD-related genes and proteins is due to disrupted COX2/PGE2 signaling. Prostacyclin (PGI2) is synthesized from arachidonic acid by metabolic-pathway-dependent cyclooxygenase (COX) and synthesized in a primary step of ARA transformation (PGG2, PGH2), by degradation of the abovementioned prostaglandins. Full article

Background: AI-driven mental health solutions offer transformative potential for improving mental healthcare outcomes, but identifying the most effective approaches remains a challenge. This study addresses this gap by evaluating and prioritizing AI-driven mental health alternatives based on key criteria, including feasibility of implementation, cost-effectiveness, scalability, ethical compliance, user satisfaction, and impact on clinical outcomes. Methods: A fuzzy multi-criteria decision-making (MCDM) model, consisting of fuzzy TOPSIS and fuzzy ARAS, was employed to rank the alternatives, while a hybridization of the two methods was used to address discrepancies between the methods, each emphasizing distinct evaluative aspect. Results: Fuzzy TOPSIS, focusing on closeness to the ideal solution, ranked personalization of care (A5) as the top alternative with a closeness coefficient of 0.50, followed by user engagement (A2) at 0.45. Fuzzy ARAS, which evaluates cumulative performance, also ranked A5 the highest, with an overall performance rating of Si = 0.90 and utility degree Qi = 0.92. Combining both methods provided a balanced assessment, with A5 retaining its top position due to high scores in user satisfaction and clinical outcomes. Conclusions: This result underscores the importance of personalization and engagement in optimizing AI-driven mental health solutions, suggesting that tailored, user-focused approaches are pivotal for maximizing treatment success and user adherence. Full article