A systematic literature review of hate speech identification on Arabic Twitter data: research challenges and future directions.

The automatic speech identification in Arabic tweets has generated substantial attention among academics in the fields of text mining and natural language processing (NLP). The quantity of studies done on this subject has experienced significant growth. This study aims to provide an overview of this field by conducting a systematic review of literature that focuses on automatic hate speech identification, particularly in the Arabic language. The goal is to examine the research trends in Arabic hate speech identification and offer guidance to researchers by highlighting the most significant studies published between 2018 and 2023. This systematic study addresses five specific research questions concerning the types of the Arabic language used, hate speech categories, classification techniques, feature engineering techniques, performance metrics, validation methods, existing challenges faced by researchers, and potential future research directions. Through a comprehensive search across nine academic databases, 24 studies that met the predefined inclusion criteria and quality assessment were identified. The review findings revealed the existence of many Arabic linguistic varieties used in hate speech on Twitter, with modern standard Arabic (MSA) being the most prominent. In identification techniques, machine learning categories are the most used technique for Arabic hate speech identification. The result also shows different feature engineering techniques used and indicates that N-gram and CBOW are the most used techniques. F1-score, precision, recall, and accuracy were also identified as the most used performance metric. The review also shows that the most used validation method is the train/test split method. Therefore, the findings of this study can serve as valuable guidance for researchers in enhancing the efficacy of their models in future investigations. Besides, algorithm development, policy rule regulation, community management, and legal and ethical consideration are other real-world applications that can be reaped from this research.

Machine learning-based technique for resonance and directivity prediction of UMTS LTE band quasi Yagi antenna.

In this study, we have presented our findings on the deployment of a machine learning (ML) technique to enhance the performance of LTE applications employing quasi-Yagi-Uda antennas at 2100 MHz UMTS band. A number of techniques, including simulation, measurement, and a model of an RLC-equivalent circuit, are discussed in this article as ways to assess an antenna's suitability for the intended applications. The CST simulation gives the suggested antenna a reflection coefficient of -38.40 dB at 2.1 GHz and a bandwidth of 357 MHz (1.95 GHz-2.31 GHz) at a -10 dB level. With a dimension of 0.535λ0×0.714λ0, it is not only compact but also features a maximum gain of 6.9 dB, a maximum directivity of 7.67, VSWR of 1.001 at center frequency and a maximum efficiency of 89.9%. The antenna is made of a low-cost substrate, FR4. The RLC circuit, sometimes referred to as the lumped element model, exhibits characteristics that are sufficiently similar to those of the proposed Yagi antenna. We use yet another supervised regression machine learning (ML) technique to create an exact forecast of the antenna's frequency and directivity. The performance of machine learning (ML) models can be evaluated using a variety of metrics, including the variance score, R square, mean square error (MSE), mean absolute error (MAE), root mean square error (RMSE), and mean squared logarithmic error (MSLE). Out of the seven ML models, the linear regression (LR) model has the lowest error and maximum accuracy when predicting directivity, whereas the ridge regression (RR) model performs the best when predicting frequency. The proposed antenna is a strong candidate for the intended UMTS LTE applications, as shown by the modeling results from CST and ADS, as well as the measured and forecasted outcomes from machine learning techniques.

TumorDetNet: A unified deep learning model for brain tumor detection and classification.

Accurate diagnosis of the brain tumor type at an earlier stage is crucial for the treatment process and helps to save the lives of a large number of people worldwide. Because they are non-invasive and spare patients from having an unpleasant biopsy, magnetic resonance imaging (MRI) scans are frequently employed to identify tumors. The manual identification of tumors is difficult and requires considerable time due to the large number of three-dimensional images that an MRI scan of one patient's brain produces from various angles. Moreover, the variations in location, size, and shape of the brain tumor also make it challenging to detect and classify different types of tumors. Thus, computer-aided diagnostics (CAD) systems have been proposed for the detection of brain tumors. In this paper, we proposed a novel unified end-to-end deep learning model named TumorDetNet for brain tumor detection and classification. Our TumorDetNet framework employs 48 convolution layers with leaky ReLU (LReLU) and ReLU activation functions to compute the most distinctive deep feature maps. Moreover, average pooling and a dropout layer are also used to learn distinctive patterns and reduce overfitting. Finally, one fully connected and a softmax layer are employed to detect and classify the brain tumor into multiple types. We assessed the performance of our method on six standard Kaggle brain tumor MRI datasets for brain tumor detection and classification into (malignant and benign), and (glioma, pituitary, and meningioma). Our model successfully identified brain tumors with remarkable accuracy of 99.83%, classified benign and malignant brain tumors with an ideal accuracy of 100%, and meningiomas, pituitary, and gliomas tumors with an accuracy of 99.27%. These outcomes demonstrate the potency of the suggested methodology for the reliable identification and categorization of brain tumors.

Knowledge, Attitudes, and Practices of the Population in Jazan Region, Saudi Arabia Regarding Dengue Fever and Its Prevention Measures: A Community-Based Cross-Sectional Study.

In previous studies, there was an apparent lack of health education about dengue fever (DF) among the Saudi population. Therefore, we conducted this study to assess the knowledge, attitude, and practices (KAP) about dengue fever among the Jazan region population, which is one of the most prevalent diseases in the region in Saudi Arabia (KSA). This was a cross-sectional and community-based study. The adult population was divided into governorates according to the regions that were close to each other, and then a convenient stratum was selected from each region. Next, random sampling was applied. Data were collected using a self-administered questionnaire. Exclusion criteria were young people (<18 years old) and health workers. Data analysis was performed using descriptive statistics, the Pearson's correlation coefficient, and multiple linear regression. Of the 392 participants in this cross-sectional study, 59.18% were male, 76.28% were aged 18-35 years, 72.96% had a university degree, and 63% had a monthly income of less than SAR 5000 (USD1 = 3.76). The scores (mean ± SD) for KAP regarding DF among the responders were 22.77 ± 7.9, 22.68 ± 7.24, and 25.62 ± 9.4, respectively. KAP constructs were positively correlated according to the Pearson's coefficient. In multiple linear regression analysis, males were favorably and substantially linked with attitude score (ß = 2.76, p = 0.001) and negatively associated with practice score (ß = -2.45, p = 0.023). No-degree participants scored lower on knowledge (ß = -2.78, p = 0.003). There is potential for more research in Saudi Arabia to increase the generalizability to reduce the impact of dengue epidemics.

Factors Associated with an Unhealthy Lifestyle among Adults in Riyadh City, Saudi Arabia.

BACKGROUND: Unhealthy lifestyles are a global concern. This study measured the prevalence and factors associated with an unhealthy lifestyle in Riyadh city, Saudi Arabia. METHODS: An interview-based, cross-sectional study was conducted with 968 males and 2029 females, aged 30-75 years, covering 18 primary health care centers in Riyadh. Multivariate logistic regression analyses were conducted to identify the significant determinants associated with an unhealthy lifestyle. RESULTS: Overall, men were 1.49 (1.28, 1.74) times at higher risk of an unhealthy lifestyle compared to women. Men reporting unhealthy lifestyle were 2.1 (1.3, 3.4) and 1.5 (1.0, 2.6) times more likely than men with healthy lifestyle to cite not enjoying physical activity, lack of social support, and not having enough information about a healthy diet [1.5 (1.0, 2.0)], whereas those ≥ 45 years age group were 30 times less likely to report unhealthy lifestyle [0.7 (0.5, 0.9)]. In contrast, in women aged ≥ 45 years [1.3 (1.1, 1.7)], lack of motivation [1.3 (1.1, 1.7)], feeling conscious while exercising [2.0 (1.4, 2.9)], not enjoying healthy food [1.6 (1.3, 2.1)], and no family support to prepare healthy food [1.4 (1.1, 1.8)] were significantly associated with an unhealthy lifestyle. CONCLUSIONS: In a Saudi sample, younger men and older women are at higher risk of an unhealthy lifestyle. In addition to self-motivation, combined strategies to promote physical activity and healthy eating are required to improve lifestyle.

Risk of General Anesthesia in Pediatric Skin Procedures with Projection on Tumescent Anesthesia.

BACKGROUND: Uses of general anaesthesia in outpatient invasive procedures have increased, especially in dermatology. Being uncooperative, children often require general anaesthesia, since surgical skin operations are mostly painful. AIM: The purpose of this study is to evaluate the safety, significant adverse events, and the complication rates related to general anaesthesia, when used among pediatric population undergoing skin procedures. METHODS: We conducted a first retrospective cohort study of patient chart review during the period from September 1, 2017 through September 2019. All patients admitted for pediatric skin procedures during this period have participated in our study. We reviewed selected charts to document any unexpected admissions, adverse events, or complications. Surgical outcomes and anaesthesia complications were reviewed by three anesthesiologists. We assessed inter-rater reliability. RESULTS: A total of 211 procedures were reported for 211 patients with 19 diagnoses. No adverse events related to anaesthesia were recognized, apart from minor complications noticed in twelve patients. The kappa value range is between 0.78 and 1.00 (95% C.I., 0.46809 to 1.00). CONCLUSION: Dermatologist and pediatricians can safely do necessary procedures under general anaesthesia with the supervision of pediatric-trained anesthesiologists while considering other safety and risk precautions and the pediatric age group.

Mammography uptake among the female staff of King Saud University.

BACKGROUND: Breast cancer is having a major impact on women's health worldwide. Early detection is the best defense against the associated morbidity and mortality of the disease. OBJECTIVES: To assess the level of mammography uptake among working Saudi women and identify the obstacles and barriers that negatively affect it. In addition, to identify the most effective sources of breast-cancer-related information and early detection screening. METHOD: We conducted a cross-sectional study of women employees of King Saud University aged 40 years and above on March-May 2015 using a self-report questionnaire. RESULTS: A total of 229 participants were recruited from the female staff of King Saud University. Of the participants, 34% were aged 41 years or above, approximately 66% were married, 53.3% had a bachelor's degree, and 61.1% worked as administrators; further, 64.6% had a history of breastfeeding. The rate of mammography uptake was 51.5%. Univariate logistic regression indicated that age, education, and being single predict the rate of mammography uptake. However, multivariate logistic regression indicated that earlier age significantly predicts a higher risk of a low rate of mammography uptake. The main obstacle negatively affecting mammography uptake was ineligible criteria (21.8%). The main sources of information regarding breast cancer were awareness campaigns and television and radio (45.4% and 43.7%, respectively). CONCLUSION: The participants' rate of mammography uptake, awareness of mammograms, the risk factors, and signs of breast cancer were low. To improve breast-cancer mortality rates in Saudi Arabia, earlier detection of breast cancer through increasing awareness of mammograms is of paramount importance.

Community's compliance with measures for the prevention of respiratory infections in Riyadh, Saudi Arabia.

BACKGROUND: Acute respiratory tract infections are the most common causes of both morbidity and mortality worldwid, and the management and prevention of acute respiratory infections is a global problem, especially in developing countries. This study sought to assess the community's compliance and practice of measures for the prevention of respiratory infections and discover their source of health information. MATERIALS AND METHODS: A cross-sectional study was carried out in the five biggest shopping malls in Riyadh city in July 2014. The required sample size was 980 persons aged 15 or older, with 196 from each of the five biggest shopping malls from each of the five geographic areas of Riyadh. Data was collected by face-to-face interview using standardised questionnaire, and analyzed using SPSS. RESULTS: Overall, 48.3% of the participants thought that they were susceptible to any of the respiratory infections of pandemic influenza; 59.7% always washed their hands with water and soap and 34.8% used antibacterial soap. About 29% reported avoiding touching their eyes, noses, and mouths directly with their hands; 63.5% covered their noses and mouths with tissue paper when sneezing or coughing. A substantial number said they "never" shared their personal stuff, including towels (70.5%) and utensils (49.0%) with others. Only 21.2% avoided crowded places or wore a mask (9.1%) in such a situation. A high proportion (62.8%) did not take the seasonal flu vaccine. The most common sources of health information included television/radio (47.9%), social media (29.4%), and friends/family (28.1%). CONCLUSIONS: Health authorities should seize every opportunity to prevent respiratory infections by adopting all evidence-based infection control measures to improve public awareness, attitude, and practice.