Identification of Fine-Grained Location Mentions in Crisis Tweets

Identification of fine-grained location mentions in crisis tweets is central in transforming situational awareness information extracted from social media into actionable information. Most prior works have focused on identifying generic locations, without considering their specific types. To facilitate progress on the fine-grained location identification task, we assemble two English tweet crisis datasets and manually annotate them with specific location types. The first dataset contains tweets from a mixed set of crisis events, while the second dataset contains tweets from the global COVID-19 pandemic. We investigate the performance of state-of-the-art deep learning models for sequence tagging on these datasets, in both in-domain and cross-domain settings.

Identification of Fine-Grained Location Mentions in Crisis Tweets

Identification of fine-grained location mentions in crisis tweets is central in transforming situational awareness information extracted from social media into actionable information. Most prior works have focused on identifying generic locations, without considering their specific types. To facilitate progress on the fine-grained location identification task, we assemble two English tweet crisis datasets and manually annotate them with specific location types. The first dataset contains tweets from a mixed set of crisis events, while the second dataset contains tweets from the global COVID-19 pandemic. We investigate the performance of state-of-the-art deep learning models for sequence tagging on these datasets, in both in-domain and cross-domain settings. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

A Fatal Case of Intraparenchymal Hemorrhage Masquerading as Central Diabetes Insipidus

This is 32-year-old women presented to us on postpartum day 10 with severe covid-19 pneumonia. Hercomplaints were dyspnea and headache which she described as, frontally located, 8/10 in intensity, non-radiating and not associated with any posture. She had no prior history of migraines. She was afebrile, tachycardiac and hypoxic on exam. Physical examination was unremarkable. Patient failed trial of non-invasive ventilation following which she was intubated. CT head on admission was unremarkable.For COVID 19 ARDS, she was started on dexamethasone, tocilizumab, paralysis was achieved withcisatracurium and prone protocol was followed for refractory hypoxia. Patient was placed on DVTprophylaxis with heparin. Her pneumonia and oxygenation improved. However, on hospital day 8, herlab results were suspicious of Diabetes insipidus (DI). Her serum sodium was 152mEq/L with serumosmolarity of 360 and polyuria (more than 2L of urine in one hour). A full neurological examinationcould not be obtained as she was paralyzed, however, pupils were equal in size and reactive to light. With high clinical suspicions of diabetes insipidus she received a one-time dose of 16mcg of DDAVP andMRI of pituitary gland was ordered to delineate etiology. Subsequent improvement in polyuria wasnoted. Despite DDAVP her serum sodium continued to worsen. We continued to monitor serumsodium levels every four hours. Her serum sodium levels remained labile with a precipitous drop notedfrom 174mEq/L to 152mEq/L. Review of Pituitary MRI revealed multiple intraparenchymal hemorrhageson bilateral frontal lobes along with trans tentorial and cerebellar tonsillar herniation. Subsequently, patient underwent a brain death exam and declared brain dead. We suspect the development of intracranial hemorrhage in our patient was secondary to covid-19. Onliterature review, an incidence of 0.2% in covid-19 patients with a mortality of 48% is reported. In ourpatient, inability to perform a full neurological exam due to paralysis limited early recognition andintervention. This case highlights the need for increased awareness in patients with features of central diabetesinsipidus and the urgency to obtain CT head immediately after a diagnosis has been established. Promptconsideration of neuroimaging should be made when features of central diabetes mellitus are noted with limited neurological exam.

Using Content Analysis and Machine Learning to Identify COVID-19 Information Relevant to Low-income Households on Social Media

COVID-19 pandemic has caused great distress in the lives of many populations. Low-income households are among the most severely impacted groups in the United States and across the globe. Using social media, this paper aims to identify and organize the information about the impact of the pandemic on low-income households. We use content analysis to derive an annotation protocol and manually annotate a tweet dataset using this protocol. Furthermore, we use machine learning to learn models from the annotated dataset. We also employ a human-in-the-loop data augmentation procedure to improve the model's performance for the underrepresented classes. Our results show that using carefully annotated data, automated machine learning models can be trained and employed to identify information relevant to low income households, potentially in real time. © 2021 IEEE.

Stance Detection in COVID-19 Tweets

The prevalence of the COVID-19 pandemic in day-to-day life has yielded large amounts of stance detection data on social media sites, as users turn to social media to share their views regarding various issues related to the pandemic, e.g. stay at home mandates and wearing face masks when out in public. We set out to make use of this data by collecting the stance expressed by Twitter users, with respect to topics revolving around the pandemic. We annotate a new stance detection dataset, called COVID-19-Stance. Using this newly annotated dataset, we train several established stance detection models to ascertain a baseline performance for this specific task. To further improve the performance, we employ self-training and domain adaptation approaches to take advantage of large amounts of unlabeled data and existing stance detection datasets. The dataset, code, and other resources are available on GitHub.(1)

The Expanded Role of Dentists in the COVID-19 Pandemic Worldwide

The COVID-19 has spread globally and ensued several global restrictions with consequences of unknown long-term proportions, currently placing a strain on the healthcare system worldwide. This review aims to present the role of dentists in the COVID-19 pandemic in various aspects of dentistry, including general dentistry and restorative dentistry. Various studies and reports on COVID-19 were analyzed. Literatures on 2019 novel coronavirus disease (COVID-19) were explored using key words “COVID-19”, “COVID”, “dentistry”, “oral health”, “oral cavity” in Google Scholar, PubMed/Medline, and Scopus databases. It was found that dentists, dental specialists, dental assistants, dental staff, and patients are potentially at higher risk of COVID-19 infection during dental treatments. There is an association between the oral cavity and systemic diseases in the context of COVID-19 disease caused by SARS-CoV-2 virus. There is a great role of dentists in the COVID-19 pandemic in various aspects of dentistry, including general dentistry and restorative dentistry © 2021, Journal of International Dental and Medical Research. All Rights Reserved.

Binding of SARS-CoV-2/SARS-CoV spike protein with human ACE2 receptor

SARS-CoV-2 virus is the serious health concern throughout the world. A comprehensive investigation of binding of SARS-CoV-2 active site with host receptor protein hACE2 is important in designing effective drugs. In the present work, the major amino acid binding partners between the virus CTD and host receptor have been studied and are compared with SARS-CoV RBD binding with hACE2. Our investigation show that some unique hydrogen bond pairs which were not reported in previous work. Along with hydrogen bonding, salt-bridges, hydrophobic interactions and contributions of electrostatic and van der Waals contacts play significant role in binding mechanism. The binding affinity of SARS-CoV-2 CTD/hACE2 is greater than SARS-CoV RBD/hACE2. This outcome is also verified from the free energy estimation by using umbrella sampling.