Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing; however, they often struggle to accurately capture and reflect cultural nuances. This research addresses this challenge by focusing on Saudi Arabia, a country characterized by diverse dialects and rich cultural traditions. We introduce SaudiCulture, a novel benchmark designed to evaluate the cultural competence of LLMs within the distinct geographical and cultural contexts of Saudi Arabia. SaudiCulture is a comprehensive dataset of questions covering five major geographical regions—West, East, South, North, and Center—along with general questions applicable across all regions. The dataset encompasses a broad spectrum of cultural domains, including food, clothing, entertainment, celebrations, and crafts. To ensure a rigorous evaluation, SaudiCulture includes questions of varying complexity, such as open-ended, single-choice, and multiple-choice formats, with some requiring multiple correct answers. Additionally, the dataset distinguishes between common cultural knowledge and specialized regional aspects. We conduct extensive evaluations on six LLMs—GPT-4, Llama 3.3, FANAR, Jais, AceGPT and DeepSeek —analyzing their performance across different question types and cultural contexts. Our findings reveal that all models experience significant performance declines when faced with highly specialized or region-specific questions, particularly those requiring multiple correct responses. Furthermore, we observe that while some regions are better understood by LLMs, others remain largely misrepresented. For instance, GPT-4 achieves the highest accuracy in the western region (66%), whereas Jais records the lowest accuracy in the northern region (16%). Additionally, certain cultural categories are more easily identifiable than others, further highlighting inconsistencies in LLMs’ cultural understanding. These results emphasize the importance of incorporating region-specific knowledge into LLMs training to enhance their cultural competence. We hope that SaudiCulture serves as a foundation for future efforts aimed at improving the ability of LLMs to engage with and accurately represent diverse cultural contexts.

Textual data are among the most popular data types that provide useful knowledge today. The need to extract insights from text has initiated and overseen the progression of research in the text mining domain. The challenge of addressing textual data comes from the complexity of text processing. The nature of text presents challenges that demand sophisticated processing methods. Subsequently, the degree of complexity involved in this field drives researchers to continuously improve the existing feature selection and extraction techniques, highlighting the essential work that is necessary to propel the field forward. Unlike the existing reviews that focus on individual components such as preprocessing, feature selection, or feature extraction in isolation, this study offers a unified perspective by integrating all three aspects. This review explores the feature selection and extraction methods advances achieved in text mining over the last decade. The focus of this investigation is the development of novel approaches that have been designed to address the complexities that accompany textual data. The comprehensive examination includes identifying the current trends and significant breakthroughs that characterize this dynamic field, thus providing a comprehensive view of the ongoing efforts to refine and optimize these methodologies. The presented explanation of the details associated with feature selection and extraction not only keeps researchers up to date on the latest developments but also contributes significantly to the ongoing refinement and growth exhibited by text mining techniques.

Multi-label text classification involves assigning multiple relevant categories to a single text, enabling applications in academic indexing, medical diagnostics, and e-commerce. However, existing models often fail to capture complex text-label relationships and lack robust mechanisms for ranking label relevance, limiting their effectiveness. This paper proposes the Label-Aware Hierarchical Ranking Model, a novel approach that combines contextual embeddings, custom attention mechanisms, and gradient boosting to enhance label ranking. The proposed model integrates text and label embeddings with a contextual similarity attention module to capture text-label relationships and inter-label dependencies, followed by a hierarchical ranking mechanism for refining label prioritization. Experiments conducted on both the ArXiv Academic Paper dataset and the Reuters-21578 dataset demonstrate that the proposed model surpasses state-of-the-art models, achieving Precision@1 scores of 86.90 % and 94.47 %, respectively. These results advance multi-label text classification methodologies, offering more accurate, context-aware, and practically applicable classifications.

Large Language Models (LLMs) have demonstrated remarkable capabilities in natural language processing; however, they often struggle to accurately capture and reflect cultural nuances. This research addresses this challenge by focusing on Saudi Arabia, a country characterized by diverse dialects and rich cultural traditions. We introduce SaudiCulture, a novel benchmark designed to evaluate the cultural competence of LLMs within the distinct geographical and cultural contexts of Saudi Arabia. SaudiCulture is a comprehensive dataset of questions covering five major geographical regions, such as West, East, South, North, and Center, along with general questions applicable across all regions. The dataset encompasses a broad spectrum of cultural domains, including food, clothing, entertainment, celebrations, and crafts. To ensure a rigorous evaluation, SaudiCulture includes questions of varying complexity, such as open-ended, single-choice, and multiple-choice formats, with some requiring multiple correct answers. Additionally, the dataset distinguishes between common cultural knowledge and specialized regional aspects. We conduct extensive evaluations on five LLMs, such as GPT-4, Llama 3.3, FANAR, Jais, and AceGPT, analyzing their performance across different question types and cultural contexts. Our findings reveal that all models experience significant performance declines when faced with highly specialized or region-specific questions, particularly those requiring multiple correct responses. Additionally, certain cultural categories are more easily identifiable than others, further highlighting inconsistencies in LLMs cultural understanding. These results emphasize the importance of incorporating region-specific knowledge into LLMs training to enhance their cultural competence.

Mental health discourse may reflect social relationships, cultural norms, and religious factors that shape how individuals express and interpret distress. Existing NLP research on mental health has advanced the detection of depression, anxiety, suicide risk, and related clinical signals using text mining, neural classification, transformer-based models, and, more recently, large language models. However, most systems treat text primarily as a clinical signal rather than examining the social and cultural contexts in which distress is expressed. Arabic NLP research remains even more limited, largely focusing on detecting clinical conditions while overlooking contextual factors that shape mental health questions. This work introduces ContextMental, a multi-label annotation schema and benchmark dataset for modeling sociocultural context in Arabic mental health questions. The dataset contains 2677 questions, including 552 instances with contextual labels, enabling fine-grained analysis of social, cultural, and religious dimensions. An AraBERT-based classification framework is further developed using imbalance-aware optimization, semi-supervised pseudo-labeling, and adaptive threshold calibration. Experimental results indicate that pseudo-label augmentation improves overall classification performance, suggesting that semi-supervised learning can support context-aware Arabic mental health classification. This study provides a context-aware annotation framework, a benchmark dataset, and an AraBERT-based baseline modeling pipeline for Arabic mental health NLP, thereby supporting future research on socially, culturally, and religiously grounded language technologies.