Hate speech detection in the Arabic language: corpus design, construction, and evaluation.

Hate Speech Detection in Arabic presents a multifaceted challenge due to the broad and diverse linguistic terrain. With its multiple dialects and rich cultural subtleties, Arabic requires particular measures to address hate speech online successfully. To address this issue, academics and developers have used natural language processing (NLP) methods and machine learning algorithms adapted to the complexities of Arabic text. However, many proposed methods were hampered by a lack of a comprehensive dataset/corpus of Arabic hate speech. In this research, we propose a novel multi-class public Arabic dataset comprised of 403,688 annotated tweets categorized as extremely positive, positive, neutral, or negative based on the presence of hate speech. Using our developed dataset, we additionally characterize the performance of multiple machine learning models for Hate speech identification in Arabic Jordanian dialect tweets. Specifically, the Word2Vec, TF-IDF, and AraBert text representation models have been applied to produce word vectors. With the help of these models, we can provide classification models with vectors representing text. After that, seven machine learning classifiers have been evaluated: Support Vector Machine (SVM), Logistic Regression (LR), Naive Bays (NB), Random Forest (RF), AdaBoost (Ada), XGBoost (XGB), and CatBoost (CatB). In light of this, the experimental evaluation revealed that, in this challenging and unstructured setting, our gathered and annotated datasets were rather efficient and generated encouraging assessment outcomes. This will enable academics to delve further into this crucial field of study.

New Phenolic Lipids from the Leaves of Clausena harmandiana Inhibit SARS-CoV-2 Entry into Host Cells.

Induced by the spread of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), the COVID-19 pandemic underlined the clear need for antivirals against coronaviruses. In an effort to identify new inhibitors of SARS-CoV-2, a screening of 824 extracts prepared from various parts of 400 plant species belonging to the Rutaceae and Annonaceae families was conducted using a cell-based HCoV-229E inhibition assay. Due to its significant activity, the ethyl acetate extract of the leaves of Clausena harmandiana was selected for further chemical and biological investigations. Mass spectrometry-guided fractionation afforded three undescribed phenolic lipids (1-3), whose structures were determined via spectroscopic analysis. The absolute configurations of 1 and 2 were determined by analyzing Mosher ester derivatives. The antiviral activity against SARS-CoV-2 was subsequently shown, with IC50 values of 0.20 and 0.05 µM for 2 and 3, respectively. The mechanism of action was further assessed, showing that both 2 and 3 are inhibitors of coronavirus entry by acting directly on the viral particle. Phenolic lipids from Clausena harmandiana might be a source of new antiviral agents against human coronaviruses.

Investigation of astrovirus, coronavirus and paramyxovirus co-infections in bats in the western Indian Ocean.

Co-infections have a key role in virus transmission in wild reservoir hosts. We investigated the simultaneous presence of astroviruses, coronaviruses, and paramyxoviruses in bats from Madagascar, Mayotte, Mozambique, and Reunion Island. A total of 871 samples from 28 bat species representing 8 families were tested by polymerase chain reactions (PCRs) targeting the RNA-dependent RNA-polymerase genes. Overall, 2.4% of bats tested positive for the presence of at least two viruses, only on Madagascar and in Mozambique. Significant variation in the proportion of co-infections was detected among bat species, and some combinations of co-infection were more common than others. Our findings support that co-infections of the three targeted viruses occur in bats in the western Indian Ocean region, although further studies are needed to assess their epidemiological consequences.