Sentiment-Based Spatiotemporal Prediction Framework for Pandemic Outbreaks Awareness Using Social Networks Data Classification

According to the World Health Organization, several factors have affected the accurate reporting of SARS-CoV-2 outbreak status, such as limited data collection resources, cultural and educational diversity, and inconsistent outbreak reporting from different sectors. Driven by this challenging situation, this study investigates the potential expediency of using social network data to develop reliable early information surveillance and warning system for pandemic outbreaks. As such, an enhanced framework of three inherently interlinked subsystems is proposed. The first subsystem includes data collection and integration mechanisms, data preprocessing, and hybrid sentiment analysis tools to identify tweet sentiment taxonomies and quantitatively estimate public awareness. The second subsystem comprises the feature extraction unit that identifies, selects, embeds, and balances feature vectors and the classifier fitting and training unit. This subsystem is designed to capture the most effective linguistic feature combinations with more spatial evidence by using a variety of approaches, including linear classifiers, MLPs, RNNs, and CNNs, as well as pre-trained word embedding algorithms. The last is the modeling and situational awareness evaluation subsystem, which measures temporal associations between pandemic-relevant social network activities and officially announced infection counts in the most hazardous geolocations. The proposed framework was developed and tested using a combination of static datasets and real-time scraped Twitter data. The results of these experiments showed the remarkable performance of the framework in assessing the temporal associations between public awareness and outbreak status. It also showed that the Decision Tree Classifier with Unigram+TF-IDF feature vectors outperformed other conventional models for sentiment classification and geolocation classification with an accuracy of 94.3% and 80.8, respectively. As indicated, conventional machine learning algorithms didn't achieve a precision of more than 80%, while, for instance, MLP with self-embedding layer, Word2Vec, and GloVe pre-trained word embedding resulted in very poor accuracy of 10%, 36%, and 32%, respectively. However, adding the PoS tag one-hot encoding embedding increased the validation accuracy from 36% to approximately 89%, while the best performance for the second subsystem was achieved by Bi-LSTM with RoBERTa word embedding, with an accuracy of 96%. The achieved results reveal that the proposed framework can proactively capture the potential hazards associated with the prevalence of infectious diseases as an effective early detection and info-surveillance awareness system.

Adverse events following immunization (AEFI) with COVID-19 vaccines: case series and literature review

There currently exists no formal consensus on advice given to patients who have experienced an adverse event following immunization (AEFI) (WHO definition) following COVID-19 vaccination. The incidence of vaccine-related cutaneous events is only likely to increase with the UK launching subsequent vaccine doses as part of the mass vaccination programme due to concerns about waning immunity. We present a small multicentre case series of 13 patients presenting with cutaneous-only AEFI from February to August 2021. Patients were between the ages of 21 and 83 years, from multiple ethnicities across secondary and tertiary care trusts in the UK and Hong Kong. The case series demonstrated a phenotypic spectrum of cutaneous manifestations not previously categorized in current literature. Along with our literature review, we have been able to surmise that cutaneous AEFI remain exceptionally rare and this should not be used as cautionary evidence against vaccination. On the contrary, better understanding of AEFI would serve to aid clinicians and patients on making informed decisions based on risk- benefit analysis. It is our aim that this pragmatic approach, taking into account multiple variable factors, would serve to aid in recommendations on vaccination as new evidence emerges over time.

Role of urban planning characteristics in forming pandemic resilient cities - Case study of Covid-19 impacts on European cities within England, Germany and Italy.

In recent decades, the world has witnessed a variety of emerging infectious diseases, some of which developed to pandemic world threatening outbreaks, the ongoing COVID-19 is known to be taking the lead in claiming lives around the globe and thus, urging people to trail its increasing figures. Therefore, this research aims to emphasize the role of urban planning in containing such outbreaks through running a series of analytical and statistical studies on European cities, worst inflicted region, to analyze the main urban features they share and that may be propagating the disease spread according to their population size, density, form, intracity connectivity and intercity connectivity. This study, as far as we know of, is the first practice to evaluate both the individual and combined impacts of these factors on recorded rates of infections. According to the context of this research, it is concluded that the diversity found in urban features are, to a large degree, related to cities being more vulnerable than others. Intracity connectivity through public transport is found to be the possible prime factor of this study, and is followed by population size, density, and intercity connectivity. Urban morphology seems to also contribute to such outbreak, with both radial and grid cities being associated to higher infections rates as to linear cities. Henceforth, setting priorities in post-pandemic urban planning schemes is essential for planning resilient cities that are capable to thrive and maintain functionality with lowest possible infections amid else possible diseases that are to follow in severity.