scholarly journals COUnty aggRegation mixup AuGmEntation (COURAGE) COVID-19 prediction

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Siawpeng Er ◽  
Shihao Yang ◽  
Tuo Zhao
Keyword(s):  
Language Processing ◽  
State Level ◽  
The United States ◽  
Short Term ◽  
Attention Model ◽  
Learning Techniques ◽  
Novel Coronavirus ◽  
Short Term Prediction ◽  
Transformer Model ◽  
Available Information

AbstractThe global spread of COVID-19, the disease caused by the novel coronavirus SARS-CoV-2, has casted a significant threat to mankind. As the COVID-19 situation continues to evolve, predicting localized disease severity is crucial for advanced resource allocation. This paper proposes a method named COURAGE (COUnty aggRegation mixup AuGmEntation) to generate a short-term prediction of 2-week-ahead COVID-19 related deaths for each county in the United States, leveraging modern deep learning techniques. Specifically, our method adopts a self-attention model from Natural Language Processing, known as the transformer model, to capture both short-term and long-term dependencies within the time series while enjoying computational efficiency. Our model solely utilizes publicly available information for COVID-19 related confirmed cases, deaths, community mobility trends and demographic information, and can produce state-level predictions as an aggregation of the corresponding county-level predictions. Our numerical experiments demonstrate that our model achieves the state-of-the-art performance among the publicly available benchmark models.

scholarly journals Short-Term Prediction of COVID-19 Cases Using Machine Learning Models

2021 ◽  
Vol 11 (9) ◽  
pp. 4266
Author(s):  
Md. Shahriare Satu ◽  
Koushik Chandra Howlader ◽  
Mufti Mahmud ◽  
M. Shamim Kaiser ◽  
Sheikh Mohammad Shariful Islam ◽  
...  
Keyword(s):  
Machine Learning ◽  
Web Application ◽  
Learning Models ◽  
Short Term ◽  
Infected People ◽  
Infected Case ◽  
First Case ◽  
Novel Coronavirus ◽  
Short Term Prediction ◽  
Machine Learning Models

The first case in Bangladesh of the novel coronavirus disease (COVID-19) was reported on 8 March 2020, with the number of confirmed cases rapidly rising to over 175,000 by July 2020. In the absence of effective treatment, an essential tool of health policy is the modeling and forecasting of the progress of the pandemic. We, therefore, developed a cloud-based machine learning short-term forecasting model for Bangladesh, in which several regression-based machine learning models were applied to infected case data to estimate the number of COVID-19-infected people over the following seven days. This approach can accurately forecast the number of infected cases daily by training the prior 25 days sample data recorded on our web application. The outcomes of these efforts could aid the development and assessment of prevention strategies and identify factors that most affect the spread of COVID-19 infection in Bangladesh.

scholarly journals Deep Learning-Based Sentiment Analysis of COVID-19 Vaccination Responses from Twitter Data

2021 ◽  
Vol 2021 ◽  
pp. 1-15
Author(s):  
Kazi Nabiul Alam ◽  
Md Shakib Khan ◽  
Abdur Rab Dhruba ◽  
Mohammad Monirujjaman Khan ◽  
Jehad F. Al-Amri ◽  
...  
Keyword(s):  
Deep Learning ◽  
Language Processing ◽  
Performance Metrics ◽  
Short Term Memory ◽  
Confusion Matrix ◽  
Short Term ◽  
Learning Techniques ◽  
The World ◽  
Long Short Term Memory ◽  
Severe Anxiety

The COVID-19 pandemic has had a devastating effect on many people, creating severe anxiety, fear, and complicated feelings or emotions. After the initiation of vaccinations against coronavirus, people’s feelings have become more diverse and complex. Our aim is to understand and unravel their sentiments in this research using deep learning techniques. Social media is currently the best way to express feelings and emotions, and with the help of Twitter, one can have a better idea of what is trending and going on in people’s minds. Our motivation for this research was to understand the diverse sentiments of people regarding the vaccination process. In this research, the timeline of the collected tweets was from December 21 to July21. The tweets contained information about the most common vaccines available recently from across the world. The sentiments of people regarding vaccines of all sorts were assessed using the natural language processing (NLP) tool, Valence Aware Dictionary for sEntiment Reasoner (VADER). Initializing the polarities of the obtained sentiments into three groups (positive, negative, and neutral) helped us visualize the overall scenario; our findings included 33.96% positive, 17.55% negative, and 48.49% neutral responses. In addition, we included our analysis of the timeline of the tweets in this research, as sentiments fluctuated over time. A recurrent neural network- (RNN-) oriented architecture, including long short-term memory (LSTM) and bidirectional LSTM (Bi-LSTM), was used to assess the performance of the predictive models, with LSTM achieving an accuracy of 90.59% and Bi-LSTM achieving 90.83%. Other performance metrics such as precision,, F1-score, and a confusion matrix were also used to validate our models and findings more effectively. This study improves understanding of the public’s opinion on COVID-19 vaccines and supports the aim of eradicating coronavirus from the world.

scholarly journals COVID-19 scenarios for the United States

2020 ◽  
Author(s):  
◽  
Simon I Hay
Keyword(s):  
United States ◽  
Model Performance ◽  
State Level ◽  
The United States ◽  
Economic Damage ◽  
Reference Scenario ◽  
Level Model ◽  
Per Capita ◽  
Novel Coronavirus ◽  
The Impact

The United States (US) has not been spared in the ongoing pandemic of novel coronavirus disease. COVID-19, caused by the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), continues to cause death and disease in all 50 states, as well as significant economic damage wrought by the non-pharmaceutical interventions (NPI) adopted in attempts to control transmission. We use a deterministic, Susceptible, Exposed, Infectious, Recovered (SEIR) compartmental framework to model possible trajectories of SARS-CoV-2 infections and the impact of NPI at the state level. Model performance was tested against reported deaths from 01 February to 04 July 2020. Using this SEIR model and projections of critical driving covariates (pneumonia seasonality, mobility, testing rates, and mask use per capita), we assessed some possible futures of the COVID-19 pandemic from 05 July through 31 December 2020. We explored future scenarios that included feasible assumptions about NPIs including social distancing mandates (SDMs) and levels of mask use. The range of infection, death, and hospital demand outcomes revealed by these scenarios show that action taken during the summer of 2020 will have profound public health impacts through to the year end. Encouragingly, we find that an emphasis on universal mask use may be sufficient to ameliorate the worst effects of epidemic resurgences in many states. Masks may save as many as 102,795 (55,898-183,374) lives, when compared to a plausible reference scenario in December. In addition, widespread mask use may markedly reduce the need for more socially and economically deleterious SDMs.

scholarly journals Political Ideology and the Outbreak of COVID-19 in the United States

2020 ◽  
Author(s):  
Daniel L. Rosenfeld
Keyword(s):  
United States ◽  
Political Ideology ◽  
State Level ◽  
The United States ◽  
The State ◽  
The Novel ◽  
Unique Role ◽  
Rapid Spread ◽  
Novel Coronavirus

At the state level within the United States, did political ideology predict the outbreak of the novel coronavirus (COVID-19)? Throughout March 2020, the United States became the epicenter of the COVID-19 pandemic, recording the most cases of any country worldwide. The current research found that, at the state level within the United States, more conservative political ideology predicted delayed implementation of stay-at-home orders and more rapid spread of COVID-19. Effects were significant across two distinct operationalizations of political ideology and held over and above relevant covariates, suggesting a potentially unique role of political ideology in the United States’ COVID-19 outbreak. Considering political ideological factors may offer valuable insights into epidemiological processes surrounding COVID-19.

scholarly journals Pandemic Politics: Timing State-Level Social Distancing Responses to COVID-19

2020 ◽  
Author(s):  
Christopher Adolph ◽  
Kenya Amano ◽  
Bree Bang-Jensen ◽  
Nancy Fullman ◽  
John Wilkerson
Keyword(s):  
Event History Analysis ◽  
State Level ◽  
The United States ◽  
The Novel ◽  
Social Distancing ◽  
Policy Responses ◽  
Original Dataset ◽  
Political Partisanship ◽  
History Analysis ◽  
Novel Coronavirus

AbstractSocial distancing policies are critical but economically painful measures to flatten the curve against emergent infectious diseases. As the novel coronavirus that causes COVID-19 spread throughout the United States in early 2020, the federal government issued social distancing recommendations but left to the states the most difficult and consequential decisions restricting behavior, such as canceling events, closing schools and businesses, and issuing stay-at-home orders. We present an original dataset of state-level social distancing policy responses to the epidemic and explore how political partisanship, COVID-19 caseload, and policy diffusion explain the timing of governors’ decisions to mandate social distancing. An event history analysis of five social distancing policies across all fifty states reveals the most important predictors are political: all else equal, Republican governors and governors from states with more Trump supporters were slower to adopt social distancing policies. These delays are likely to produce significant, on-going harm to public health.

scholarly journals Creating COVID-19 Stigma by Referencing the Novel Coronavirus as the “Chinese virus” on Twitter: Quantitative Analysis of Social Media Data (Preprint)

2020 ◽  
Author(s):  
Henna Budhwani ◽  
Ruoyan Sun
Keyword(s):  
New York ◽  
Quantitative Analysis ◽  
National Level ◽  
State Level ◽  
Fold Increase ◽  
The United States ◽  
The Novel ◽  
Structural Force ◽  
Novel Coronavirus ◽  
Derivatives Of

BACKGROUND Stigma is the deleterious, structural force that devalues members of groups that hold undesirable characteristics. Since stigma is created and reinforced by society—through in-person and online social interactions—referencing the novel coronavirus as the “Chinese virus” or “China virus” has the potential to create and perpetuate stigma. OBJECTIVE The aim of this study was to assess if there was an increase in the prevalence and frequency of the phrases “Chinese virus” and “China virus” on Twitter after the March 16, 2020, US presidential reference of this term. METHODS Using the Sysomos software (Sysomos, Inc), we extracted tweets from the United States using a list of keywords that were derivatives of “Chinese virus.” We compared tweets at the national and state levels posted between March 9 and March 15 (preperiod) with those posted between March 19 and March 25 (postperiod). We used Stata 16 (StataCorp) for quantitative analysis, and Python (Python Software Foundation) to plot a state-level heat map. RESULTS A total of 16,535 “Chinese virus” or “China virus” tweets were identified in the preperiod, and 177,327 tweets were identified in the postperiod, illustrating a nearly ten-fold increase at the national level. All 50 states witnessed an increase in the number of tweets exclusively mentioning “Chinese virus” or “China virus” instead of coronavirus disease (COVID-19) or coronavirus. On average, 0.38 tweets referencing “Chinese virus” or “China virus” were posted per 10,000 people at the state level in the preperiod, and 4.08 of these stigmatizing tweets were posted in the postperiod, also indicating a ten-fold increase. The 5 states with the highest number of postperiod “Chinese virus” tweets were Pennsylvania (n=5249), New York (n=11,754), Florida (n=13,070), Texas (n=14,861), and California (n=19,442). Adjusting for population size, the 5 states with the highest prevalence of postperiod “Chinese virus” tweets were Arizona (5.85), New York (6.04), Florida (6.09), Nevada (7.72), and Wyoming (8.76). The 5 states with the largest increase in pre- to postperiod “Chinese virus” tweets were Kansas (n=697/58, 1202%), South Dakota (n=185/15, 1233%), Mississippi (n=749/54, 1387%), New Hampshire (n=582/41, 1420%), and Idaho (n=670/46, 1457%). CONCLUSIONS The rise in tweets referencing “Chinese virus” or “China virus,” along with the content of these tweets, indicate that knowledge translation may be occurring online and COVID-19 stigma is likely being perpetuated on Twitter.

scholarly journals Creating COVID-19 Stigma by Referencing the Novel Coronavirus as the “Chinese virus” on Twitter: Quantitative Analysis of Social Media Data

10.2196/19301 ◽  
2020 ◽  
Vol 22 (5) ◽  
pp. e19301 ◽  
Author(s):  
Henna Budhwani ◽  
Ruoyan Sun
Keyword(s):  
New York ◽  
Quantitative Analysis ◽  
National Level ◽  
State Level ◽  
Fold Increase ◽  
The United States ◽  
The Novel ◽  
Structural Force ◽  
Novel Coronavirus ◽  
Derivatives Of

Background Stigma is the deleterious, structural force that devalues members of groups that hold undesirable characteristics. Since stigma is created and reinforced by society—through in-person and online social interactions—referencing the novel coronavirus as the “Chinese virus” or “China virus” has the potential to create and perpetuate stigma. Objective The aim of this study was to assess if there was an increase in the prevalence and frequency of the phrases “Chinese virus” and “China virus” on Twitter after the March 16, 2020, US presidential reference of this term. Methods Using the Sysomos software (Sysomos, Inc), we extracted tweets from the United States using a list of keywords that were derivatives of “Chinese virus.” We compared tweets at the national and state levels posted between March 9 and March 15 (preperiod) with those posted between March 19 and March 25 (postperiod). We used Stata 16 (StataCorp) for quantitative analysis, and Python (Python Software Foundation) to plot a state-level heat map. Results A total of 16,535 “Chinese virus” or “China virus” tweets were identified in the preperiod, and 177,327 tweets were identified in the postperiod, illustrating a nearly ten-fold increase at the national level. All 50 states witnessed an increase in the number of tweets exclusively mentioning “Chinese virus” or “China virus” instead of coronavirus disease (COVID-19) or coronavirus. On average, 0.38 tweets referencing “Chinese virus” or “China virus” were posted per 10,000 people at the state level in the preperiod, and 4.08 of these stigmatizing tweets were posted in the postperiod, also indicating a ten-fold increase. The 5 states with the highest number of postperiod “Chinese virus” tweets were Pennsylvania (n=5249), New York (n=11,754), Florida (n=13,070), Texas (n=14,861), and California (n=19,442). Adjusting for population size, the 5 states with the highest prevalence of postperiod “Chinese virus” tweets were Arizona (5.85), New York (6.04), Florida (6.09), Nevada (7.72), and Wyoming (8.76). The 5 states with the largest increase in pre- to postperiod “Chinese virus” tweets were Kansas (n=697/58, 1202%), South Dakota (n=185/15, 1233%), Mississippi (n=749/54, 1387%), New Hampshire (n=582/41, 1420%), and Idaho (n=670/46, 1457%). Conclusions The rise in tweets referencing “Chinese virus” or “China virus,” along with the content of these tweets, indicate that knowledge translation may be occurring online and COVID-19 stigma is likely being perpetuated on Twitter.

scholarly journals More Active Internet-Search on Google and Twitter Posting for COVID-19 Corresponds with Lower Infection Rate in the 50 U.S. States

2020 ◽  
Author(s):  
Jiachen Sun ◽  
Peter Gloor
Keyword(s):  
Infection Rate ◽  
Predictive Accuracy ◽  
State Level ◽  
The United States ◽  
The Novel ◽  
Internet Search ◽  
Online Social Media ◽  
Lower Infection ◽  
Novel Coronavirus ◽  
Lower Infection Rate

Abstract As the novel coronavirus disease 2019 (COVID-19) continues to rage worldwide, the United States has become the most affected country with more than 2.5 million total confirmed cases up to now (June 2, 2020). In this work, we investigate the predictive power of online social media and Internet search for the COVID-19 pandemic among 50 U.S. states. By collecting the state-level daily trends through both Twitter and Google Trends, we observe a high but state-different lag correlation with the number of daily confirmed cases. We further find that the predictive accuracy measured by the correlation coefficient is positively correlated to a state’s demographic, air traffic volume and GDP development. Most importantly, we show that a state’s early infection rate is negatively correlated with the lag to the previous peak in Internet search and tweeting about COVID-19, indicating that the earlier the collective awareness on Twitter/Google in a state, the lower is the infection rate.

Sign in / Sign up

Export Citation Format

Share Document