ABSTRACT
Along with the unprecedented impact of the COVID-19 pandemic on human lives, a new crisis of fake and false information related to disease has also emerged. Primarily, social media platforms such as Twitter are used to disseminate fake information due to ease of access and their large audience. However, automatic detection and classification of fake tweets is challenging task due to the complexity and lack of contextual features of short text. This paper proposes a novel CoviFake framework to classify and analyze fake tweets related to COVID-19 using vocabulary and non-vocabulary features. For this purpose, first, we combine and enhance 'CTF' and 'COVID19 Rumor' datasets to build our COVID19-sham dataset containing 25,388 labelled tweets. Next, we extract the vocabulary and 12 non-vocabulary features to compare the performance of six state-of-the-art machine learning classifiers. Our results highlight that the Random Forest (RF) classifier achieves the highest accuracy of 94.53% with the combination of top 2,000 vocabulary and 12 non-vocabulary features. In addition, we developed a large-scale dataset of CoviTweets containing 7.88 million English tweets posted by 3.8 million users during two months (March-April, 2020). The analysis of CoviTweets leveraging our framework reveals that the dataset contains 1.64 million (20.87%) fake tweets. Furthermore, we perform an in-depth examination by assigning a 'fakeness score' to hashtags and users in CoviTweets. © 2022 IEEE.
ABSTRACT
Objective: To study the relationship of ABO blood group type and COVID -19 infection susceptibility in PAF hospital Mushaf, Sargodha Introduction: The novel corona virus disease COVID-19 has spread around the world rapidly and declared as a pandemic by WHO, which still continues to outrage. Virus is contagious and spreads and in severe cases can lead to acute respiratory distress syndrome, septic shock, and even death. Viral infection and ABO blood groups are found to be associated from previous literature, as ABO blood group serve as receptor or co receptor for many viral and bacterial organisms. Methodology: Retrospective observational study in which 390 individuals including serving personnel, their dependents, retired and the civilians of all age groups and both genders residing in the premises of PAF Air Base Mushaf, Sargodha” who were tested positive for COVID screenings were included. Blood group was identified by laboratory testing. Data was analyzed using SPSS. Results: Initially screened 690 patients showed 390 were tested positive for COVID-19, blood group A+Ve, A–Ve and B+Ve were associated with higher risk for acquiring COVID-19 infection (P-value of <0.05), whereas blood group B-Ve, O+Ve, O-Ve, AB+Ve and AB-Ve has no association with COVID- 19 infection (Pvalue of >0.05). Conclusion: Our findings suggest that among COVID-19 confirmed patients, patients with B+ blood group had high susceptibility while patients with AB- blood group has minimal susceptibility to COVID-19 patients. The application of these relationships in clinical practice requires more exploratory studies.