A Novel Framework to Forecast COVID-19 Incidence Based on Google Trends Search Data

The global outbreak of coronavirus disease 2019 (COVID-19) has spread to more than 200 countries worldwide, leading to severe health and socioeconomic consequences. As such, the topic of monitoring and predicting epidemics has been attracting a lot of interest. Previous work reported search volumes from Google Trends are beneficial in decoding influenza dynamics, implying its potential for COVID-19 prediction. Therefore, a predictive model using the Wiener methods was built based on epidemic-related search queries from Google Trends, along with climate variables, aiming to forecast the dynamics of the weekly COVID-19 incidence in Washington, DC, USA. The Wiener model, which shares the merits of interpretability, low computation costs, and adaptation to nonlinear fluctuations, was used in this study. Models with multiple sets of features were constructed and further optimized by the highest weight selecting strategy. Furthermore, comparisons to the other two commonly used prediction models based on the autoregressive integrated moving average (ARIMA) and long short-term memory (LSTM) were also performed. Our results showed the predicted COVID-19 trends significantly correlated with the actual (rho <inline-formula> <tex-math notation="LaTeX">$=$</tex-math> </inline-formula> 0.88, <inline-formula> <tex-math notation="LaTeX">$p $</tex-math> </inline-formula> <inline-formula> <tex-math notation="LaTeX">$<$</tex-math> </inline-formula> 0.0001), outperforming those with ARIMA and LSTM approaches, indicating Google Trends data as a useful tool in terms of COVID-19 prediction. Also, the model using 20 search queries with the highest weighting outperformed all other models, supporting the highest weight feature selection as a feasible criterion. Google Trends search query data can be used to forecast the outbreak of COVID-19, which might assist health policymakers to allocate health care resources and taking preventive strategies. IEEE

Dense Feature Memory Augmented Transformers for COVID-19 Vaccination Search Classification

With the devastating outbreak of COVID-19, vaccines are one of the crucial lines of defense against mass infection in this global pandemic. Given the protection they provide, vaccines are becoming mandatory in certain social and professional settings. This paper presents a classification model for detecting COVID-19 vaccination related search queries, a machine learning model that is used to generate search insights for COVID-19 vaccinations. The proposed method combines and leverages advancements from modern state-of-the-art (SOTA) natural language understanding (NLU) techniques such as pretrained Transformers with traditional dense features. We propose a novel approach of considering dense features as memory tokens that the model can attend to. We show that this new modeling approach enables a significant improvement to the Vaccine Search Insights (VSI) task, improving a strong well-established gradient-boosting baseline by relative +15% improvement in F1 score and +14% in precision. © 2022 Association for Computational Linguistics.

Using weather factors and google data to predict COVID-19 transmission in Melbourne, Australia: A time-series predictive model.

Background: Forecast models have been essential in understanding COVID-19 transmission and guiding public health responses throughout the pandemic. This study aims to assess the effect of weather variability and Google data on COVID-19 transmission and develop multivariable time series AutoRegressive Integrated Moving Average (ARIMA) models for improving traditional predictive modelling for informing public health policy. Methods: COVID-19 case notifications, meteorological factors and Google data were collected over the B.1.617.2 (Delta) outbreak in Melbourne, Australia from August to November 2021. Timeseries cross-correlation (TSCC) was used to evaluate the temporal correlation between weather factors, Google search trends, Google Mobility data and COVID-19 transmission. Multivariable time series ARIMA models were fitted to forecast COVID-19 incidence and Effective Reproductive Number (R eff ) in the Greater Melbourne region. Five models were fitted to compare and validate predictive models using moving three-day ahead forecasts to test the predictive accuracy for both COVID-19 incidence and R eff over the Melbourne Delta outbreak. Results: Case-only ARIMA model resulted in an R squared (R2) value of 0.942, Root Mean Square Error (RMSE) of 141.59, and Mean Absolute Percentage Error (MAPE) of 23.19. The model including transit station mobility (TSM) and maximum temperature (Tmax) had greater predictive accuracy with R2 0.948, RMSE 137.57, and MAPE 21.26. Conclusion: Multivariable ARIMA modelling for COVID-19 cases and R eff was useful for predicting epidemic growth, with higher predictive accuracy for models including TSM and Tmax. These results suggest that TSM and Tmax would be useful for further exploration for developing weather-informed early warning models for future COVID-19 outbreaks with potential application for the inclusion of weather and Google data with disease surveillance in developing effective early warning systems for informing public health policy and epidemic response.

ArCOV-19: The First Arabic COVID-19 Twitter Dataset with Propagation Networks

In this paper, we present ArCOV-19, an Arabic COVID-19 Twitter dataset that spans one year, covering the period from 27th of January 2020 till 31st of January 2021. ArCOV-19 is the first publicly-available Arabic Twitter dataset covering COVID-19 pandemic that includes about 2.7M tweets alongside the propagation networks of the most-popular subset of them (i.e., most-retweeted and-liked). The propagation networks include both retweets and conversational threads (i.e., threads of replies). ArCOV-19 is designed to enable research under several domains including natural language processing, information retrieval, and social computing. Preliminary analysis shows that ArCOV-19 captures rising discussions associated with the first reported cases of the disease as they appeared in the Arab world. In addition to the source tweets and propagation networks, we also release the search queries and languageindependent crawler used to collect the tweets to encourage the curation of similar datasets. © WANLP 2021 - 6th Arabic Natural Language Processing Workshop

Indian Public Interest and Anxiety Surge in COVID-19 Subsequent to a Strong Epidemic in Italy and Spain through a Survey using Google Trends

A new Coronavirus has caused panic wave among the public all over the world. It is being discussed extensively in various news channels and papers each day. The most affected countries are China, Italy, Spain, and USA. In India, more than 5000 cases have been reported and the number is increasing day by day. This paper has undertaken good use of Google Trends to analyse the public interest in COVID-19 outbreak. Google Trends has been used to collect data pertaining to Indian public interest in Corona Virus.Methods: Current data pertaining to public interest in Corona virus is extracted from Google Trends website by entering the search topic: COVID-19 with location set as India. The reported period is 10th March 2020 to 8th April 2020. The second data regarding mental health query of Indians is also extracted from the same tool.Results: As per the Google Trends observed for Indian public interest in COVID-19, the interest started rising from 10th March, 2020 and was gradually moving up till 21stMarch 2020 while number of reported corona cases in India had started emerging and lockdown was enforced on the public movement. The interest in COVID-19 doubled in just a time of one week from 21st march, 2020.Similar trend has been found with Indian mental hearth search queries showing first peak on 13th March, second on 19th and third on 24th March 2020. The last peak which is highest one involves almost triple population than the first peak. Hence Google trends can be used to predict the mental health and sensitivity of the people towards disease. © 2021 IEEE.

INKAD COVID-19 IntelliSearch: A multilingual search engine for answering questions about COVID-19 in real-time from the scientific literature

Thousands of research papers on COVID-19 have been published since the start of the pandemic. To find relevant information in this vast literature, researchers and healthcare information professionals, spend increasingly more time per search query. In this paper, we present INKAD COVID-19 IntelliSearch, a multilingual search engine that we built to help researchers and healthcare information professionals in finding precise and relevant information from the COVID-19 literature in real-time, while considerably reducing time spent per search query. We used the COVID-19 Open Research Dataset as the main source of papers. The search engine has a BM25 based document retrieval component, and a neural question-answering component returning the exact answer span. The overall system is evaluated against a COVID-19 question-answering test set with different information retrieval and question-answering models. We have made INKAD COVID-19 IntelliSearch accessible online for broader use by researchers and medical information professionals. © 2021 IEEE.

Economic consequences of the COVID-19 impact on the tourism development in arctic regions of Russia

The authors assess the economic impact of the restrictions caused by the COVID-19 pandemic on the compo-nents of tourism and recreation system in the Arctic regions of Russia. They propose the estimation method, which includes indicators of changes in the sale volume and structure of the tourism industry services, changes in the revenue volume and share of tour operators, changes in the monopolization level and the distribution structure of market shares of tour operators in the Arctic regions. The study results can be used to adjust policy and strategic documents for tourism development in the Arctic regions of Russia. © Konyshev E. V., Lutoshkina A. K., 2021.

Association of Search Query Interest in Gastrointestinal Symptoms With COVID-19 Diagnosis in the United States: Infodemiology Study.

BACKGROUND: Coronavirus disease (COVID-19) is a novel viral illness that has rapidly spread worldwide. While the disease primarily presents as a respiratory illness, gastrointestinal symptoms such as diarrhea have been reported in up to one-third of confirmed cases, and patients may have mild symptoms that do not prompt them to seek medical attention. Internet-based infodemiology offers an approach to studying symptoms at a population level, even in individuals who do not seek medical care. OBJECTIVE: This study aimed to determine if a correlation exists between internet searches for gastrointestinal symptoms and the confirmed case count of COVID-19 in the United States. METHODS: The search terms chosen for analysis in this study included common gastrointestinal symptoms such as diarrhea, nausea, vomiting, and abdominal pain. Furthermore, the search terms fever and cough were used as positive controls, and constipation was used as a negative control. Daily query shares for the selected symptoms were obtained from Google Trends between October 1, 2019 and June 15, 2020 for all US states. These shares were divided into two time periods: pre-COVID-19 (prior to March 1) and post-COVID-19 (March 1-June 15). Confirmed COVID-19 case numbers were obtained from the Johns Hopkins University Center for Systems Science and Engineering data repository. Moving averages of the daily query shares (normalized to baseline pre-COVID-19) were then analyzed against the confirmed disease case count and daily new cases to establish a temporal relationship. RESULTS: The relative search query shares of many symptoms, including nausea, vomiting, abdominal pain, and constipation, remained near or below baseline throughout the time period studied; however, there were notable increases in searches for the positive control symptoms of fever and cough as well as for diarrhea. These increases in daily search queries for fever, cough, and diarrhea preceded the rapid rise in number of cases by approximately 10 to 14 days. The search volumes for these terms began declining after mid-March despite the continued rises in cumulative cases and daily new case counts. CONCLUSIONS: Google searches for symptoms may precede the actual rises in cases and hospitalizations during pandemics. During the current COVID-19 pandemic, this study demonstrates that internet search queries for fever, cough, and diarrhea increased prior to the increased confirmed case count by available testing during the early weeks of the pandemic in the United States. While the search volumes eventually decreased significantly as the number of cases continued to rise, internet query search data may still be a useful tool at a population level to identify areas of active disease transmission at the cusp of new outbreaks.

Can Users Search Trends Predict People Scares or Disease Breakout? An Examination of Infectious Skin Diseases in the United States.

BACKGROUND: In health and medicine, people heavily use the Internet to search for information about symptoms, diseases, and treatments. As such, the Internet information can simulate expert medical doctors, pharmacists, and other health care providers. AIM: This article aims to evaluate a dataset of search terms to determine whether search queries and terms can be used to reliably predict skin disease breakouts. Furthermore, the authors propose and evaluate a model to decide when to declare a particular month as Epidemic at the US national level. METHODS: A Model was designed to distinguish a breakout in skin diseases based on the number of monthly discovered cases. To apply this model, the authors correlated Google Trends of popular search terms with monthly reported Rubella and Measles cases from Centers for Disease Control and Prevention (CDC). Regressions and decision trees were used to determine the impact of different terms to trigger the occurrence of epidemic classes. RESULTS: Results showed that the volume of search keywords for Rubella and Measles rises when the volume of those reported diseases rises. Results also implied that the overall process was successful and should be repeated with other diseases. Such process can trigger different actions or activities to be taken when a certain month is declared as "Epidemic." Furthermore, this research has shown great interest for vaccination against Measles and Rubella. CONCLUSIONS: The findings suggest that the search queries and keyword trends can be truly reliable to be used for the prediction of disease outbreaks and some other related knowledge extraction applications. Also search-term surveillance can provide an additional tool for infectious disease surveillance. Future research needs to re-apply the model used in this article, and researchers need to question whether characterizing the epidemiology of Coronavirus Disease 2019 (COVID-19) pandemic waves in United States can be done through search queries and keyword trends.