Background Knowing the seroprevalence of SARS-CoV-2 IgG antibodies across geographic regions before vaccine administration is one key piece of knowledge to achieve herd immunity. While people of all ages, occupations, and communities are at risk of getting infected with SARS-CoV-2, the health care workers (HCWs) are possibly at the highest risk. Most seroprevalence surveys with HCWs conducted worldwide have been limited to Europe, North America, and East Asia. We aimed to understand how the seroprevalence of SARS-CoV-2 IgG antibodies varied across these geographic regions among HCWs based on the available evidences. Methods By searching through PubMed, ScienceDirect, and Google Scholar databases, eligible studies published from January 1, 2020 to January 15, 2021 were included for the systematic review and meta-analysis. The random-effects model was used to estimate the pooled proportion of IgG seropositive HCWs. Publication bias was assessed by funnel plot and confirmed by Egger's test. Heterogeneity was quantified using I 2 statistics. We performed sensitivity analyses based on sample size, diagnostic method and publication status. The study protocol was registered with PROSPERO (CRD42020219086). Findings A total of 53 peer-reviewed articles were selected, including 173,353 HCWs (32.7% male) from the United States, ten European, and three East Asian countries. The overall seropositive prevalence rate of IgG antibodies was 8.6% in these regions (95% CI= 7.2–9.9%). Pooled seroprevalence of IgG antibodies was higher in studies conducted in the USA (12.4%, 95% CI= 7.8–17%) than in Europe (7.7%, 95% CI=6.3–9.2%) and East Asia (4.8%, 95% CI=2.9–6.7%). The subgroup study also estimated that male HCWs had 9.4% (95% CI= 7.2–11.6%) IgG seroconversion, and female HCWs had 7.8% (95% CI=5.9–9.7%). The study exhibits a high prevalence of IgG antibodies among HCWs under 40 years in the USA, conversely, it was high in older HCWs (≥40 years of age) in Europe and East Asia. In the months February-April 2020, the estimated pooled seroprevalence was 5.7% (4.0–7.4%) that increased to 8·2% (6.2–10%) in April-May and further to 9.9% (6.9–12.9%) in the May-September time-period. Interpretation In the view of all evidence to date, a significant variation in the prevalence of SARS-CoV-2 antibodies in HCWs is observed in regions of Europe, the United States, and East Asia. The patterns of IgG antibodies by time, age, and gender suggest noticeable regional differences in transmission of the virus. Based on the insights driven from the analysis, priority is required for effective vaccination for older HCWs from Europe and East Asia. A considerable high seroprevalence of IgG among HCWs from the USA suggests a high rate of past infection that indicates the need to take adequate measures to prevent hospital spread. Moreover, the seroprevalence trend was not substantially changed after May 2020, suggesting a slow ...

No abstract

The recent surge of social media networks has provided a channel to gather and publish vital medical and health information. The focal role of these networks has become more prominent in periods of crisis, such as the recent pandemic of COVID-19. These social networks have been the leading platform for broadcasting health news updates, precaution instructions, and governmental procedures. They also provide an effective means for gathering public opinion and tracking breaking events and stories. To achieve location-based analysis for social media input, the location information of the users must be captured. Most of the time, this information is either missing or hidden. For some languages, such as Arabic, the users’ location can be predicted from their dialects. The Arabic language has many local dialects for most Arab countries. Natural Language Processing (NLP) techniques have provided several approaches for dialect identification. The recent advanced language models using contextual-based word representations in the continuous domain, such as BERT models, have provided significant improvement for many NLP applications. In this work, we present our efforts to use BERT-based models to improve the dialect identification of Arabic text. We show the results of the developed models to recognize the source of the Arabic country, or the Arabic region, from Twitter data. Our results show 3.4% absolute enhancement in dialect identification accuracy on the regional level over the state-of-the-art result. When we excluded the Modern Standard Arabic (MSA) set, which is formal Arabic language, we achieved 3% absolute gain in accuracy between the three major Arabic dialects over the state-of-the-art level. Finally, we applied the developed models on a recently collected resource for COVID-19 Arabic tweets to recognize the source country from the users’ tweets. We achieved a weighted average accuracy of 97.36%, which proposes a tool to be used by policymakers to support country-level disaster-related activities.

No abstract

The problem of identifying sentiment from customers' reviews has been an important issue for many years. Previously, different machine learning methods have been utilized to automatically categorize users' reviews into polarity levels such as positive, negative, or neutral. However, these methods suffer from low accuracy and recall. This paper presents an ensemble learning method using stacking generalization to build an accurate model for predicting sentiment polarity from social reviews. The basic concept of stacked generalization is fusing the output of a first-level classifier with a second-level classifier in a stacking manner. The diversity among the base classifiers with different features and weight measures is investigated in two domains (Twitter and Amazon product reviews), which provides a space for improving sentiment classification performance. Four types of singular classifiers: namely, support vector machine, boosted decision tree, Bayes point machine, and averaged perceptron, are used to build a two-staged and stacking model. The performance of singular and two-staged classifiers is compared with the proposed stacking model. The experiment results demonstrate that the stacking model outperforms the singular and two-staged classifiers on both datasets in terms of accuracy, precision, recall, and F1-score.