Respiratory viruses known as coronaviruses infect people and cause death. The multiple crown-like spikes on the virus’s surface give them the name “corona”. The pandemic has resulted in a global health crisis and it is expected that every year we will have to fight against different COVID-19 variants. In this critical situation, the existence of COVID-19 vaccinations provides hope for mankind. Despite severe vaccination campaigns and recommendations from health experts and the government, people have perceptions regarding vaccination risks and share their views and experiences on social media platforms. Social attitudes to these types of vaccinations are influenced by their positive and negative effects. The analysis of such opinions can help to determine social trends and formulate policies to increase vaccination acceptance. This study presents a methodology for sentiment analysis of the global perceptions and perspectives related to COVID-19 vaccinations. The research is performed on five vaccinations that include Sinopharm, Pfizer, Moderna, AstraZeneca, and Sinovac on the Twitter platform extracted using Twitter crawling. To effectively perform this research, tweets datasets are categorized into three groups, i.e., positive, negative and natural. For sentiment classification, different machine learning classifiers are used such as Random Forest (RF), Naive Bayes (NB), Decision Tree (DT), Logistic Regression (LR), and Support Vector Machine (SVM). It should be noted that the Decision tree classifier achieves the highest classification performance in all datasets as compared to the other machine learning algorithms. For COVID-19 Vaccine Tweets with Sentiment Annotation (CVSA), the highest accuracy obtained is 93.0%, for the AstraZeneca vaccine dataset 90.94%, for the Pfizer vaccine dataset 91.07%, 88.01% accuracy for the Moderna vaccine dataset, for the Sinovac vaccine dataset 92.8% accuracy, and 93.87% accuracy for the Sinopharm vaccine dataset, respectively. The quantitative comparisons demonstrate that the proposed research achieves better accuracy as compared to state-of-the-art research.

In today’s digital world, social media platforms generate a plethora of unstructured information. However, for low-resource languages like Urdu, there is a scarcity of well-structured data for specific tasks such as event classification. Urdu, a language prominent in South Asia, has boasted a complex morphological structure with unique features but has lacked standard linguistic resources like datasets. Long-text classification has demanded more effort than short-text classification due to its expansive vocabulary, information redundancy, and noise. Text processing has been the latest trend in research, with many machine learning and deep learning techniques widely used for it. Multiclass classification has been utilized to classify different languages for various purposes. In this research, a multiclass classification for the Urdu language was performed using a text dataset taken from five different social media platforms including Geo News, Samaa News, Dawn News, Express News, and Urdu Blogs totaling 103,771 sentences. We used sentence-level classification to categorize sentences including terrorist attacks, national news, sports, entertainment, politics, safety, earthquakes, fraud and corruption, sexual assault, weather, accidents, forces, inflation, murder and death, education, and international news. Deep learning, transformer-based and machine learning classifiers are used for event classification. The SMFCNN classifier achieved the greatest accuracy of 88.29%. We incorporated transformer-based models, with the proposed XLM-R+ model demonstrating superior performance with an accuracy of 89.8%. Our results were compared to previously reported techniques that used traditional models, highlighting the significant improvements offered by our approaches. The novelty of this research lies in the inclusion of 16 event categories to broaden coverage and the implementation of the SMFCNN and transformer-based algorithms. This study highlights the potential of deep learning and transformer-based models in enhancing the accuracy and generalizability of multiclass classification in low-resource languages Urdu.

Magnetic Resonance Imaging is one of the most commonly used neuro-oncology imaging modalities, which is a non-invasive mode of imaging and helps in detecting brain abnormalities in an effective way. Earlier researchers have demonstrated that brain tumor segmentation and classification can be effectively performed using deep learning techniques. Existing studies are primarily aimed at increasing prediction accuracy and provide insignificant consideration to model interpretability, limiting their practical application in clinical practice. To address this limitation, this research presents a two-stage explainable deep learning model, which combines transformer-based segmentation with an ensemble classification model that is consistent in explanations. The first stage introduces Swin-DS-HAFUNetv2, an enhanced transformer-based segmentation architecture that integrates hierarchical Swin Transformer encoders, refined hierarchical attention fusion, a contextual bottleneck transformer, and multi-scale deep supervision to improve tumor localization in T1-weighted MRI, particularly under low-contrast and irregular morphological conditions. The second stage includes the ECWMEv2 ensemble classifier, which integrates a perturbation analysis based on Grad-CAM (Gradient-weighted Class Activation Mapping) to systematically assess the consistency and clinical significance of visual explanations for candidate models. Only those architectures that exhibit stable and pathology-consistent explanations, such as ConvNeXt, Swin Transformer, and EVA02, are stored and merged by means of explanation-weighted soft voting with XGBoost-based meta-learning. Experimental evaluation on the BRISC2025 benchmark dataset indicates that Swin-DS-HAFUNetv2 has a mean Dice coefficient of 0.9782 and Intersection over Union (IoU) of 0.8656, with ECWMEv2 having a classification accuracy of 0.9917 and a Macro-F1 score of 0.9867. The mean Grad-CAM IoU of 0.692 reflects uniform and anatomically significant consistency of attention to tumor regions. These results demonstrate that the integration of explanation stability as a fundamental design principle significantly improves model robustness and interpretability to provide a methodologically validated and benchmark-level framework for future studies of multimodal and clinically oriented brain tumor analysis systems.