COVID-19 and Haters - A User Model Perspective

In this study, we present an in-depth analysis of users' propensity toward negative and hateful behavior during the COVID-19 pandemic. We analyze a large dataset extracted from Twitter from the months of January 2020 up until June 2020. The dataset includes 2,470,888 tweets from 3,269 users who are active over a period of six months. We model users' propensity toward hateful content over time by leveraging Random Forest regressor model and Long Short-Term Memory (LSTM) based many-to-one and Sequence2Sequence models for both short and long-term predictions. Our models leverage a set of features for each user, including the user's psychological traits. We also study the impact of external triggers, such as COVID-related news concurrent with the users' activities. To encode popular news, we propose using encoder states of a Sequence2Sequence model as features for a Tree-based regressor. The regressor, when combined with the vectorized news, results in an accurate prediction of tweeter's hateful behavior in the short (decoder size of four weeks) and long term (decoder size of 10 weeks) with a total training data of 15 weeks x 3269 users. We also show that our model accurately profiles selected groups of users, as they are defined by specific psychological traits. © 2022 IEEE.

Epidemiological Modeling with Sir and Arima Dynamic Models and Machine Learning to Predict the Future Behavior of Covid-19 in Panama

Mathematical models SIR and ARIMA were used, within an epidemiological approach, to adjust them to the COVID-19 pandemic data in Panama to establish a scientific criterion for taking decisions for the effects control that this pandemic has brought. Based on the predictions made from the adjustments of these models, it was concluded that they can be adjusted correctly to the data, allowing to make short-term predictions in a satisfactory way, however, if a more accurate model were to be carried out, independent variables could be included, besides time, such as mobility restrictions. This work lays down the foundations for future investigations of epidemiological models in Panama due to its exposition of mathematical model's comparison used to analyze the behavior of the COVID-19 Pandemic. Jupyter Notebook, GitHub, Machine Learning libraries and mathematical software such as Wolfram Mathematica were used. Adjustment of data was performed through statistical techniques and, for this prediction, statistical software Minitab and E-Views were also used. © 2022 IEEE.

On-line platform for the short-term prediction of risk of expansion of epidemics: Proof-of-concept based on COVID-19 evolution

This paper proposes a novel approach for the prediction of the risk of expansion of local epidemics to 3rd regions or countries in the world through the air traffic network. The approach relies on the definition of a new indicator, the Imported Risk, which represents the overall risk of having infected individuals entering an airport from any other airport with connections. We performed a proof-of-concept of the proposed approach by using daily data of the air traffic movements on a global scale and of the evolution of the COVID-19 epidemic at the beginning of 2020. For that purpose, we developed a complex network model based on Tagged Graphs to calculate the Imported Risk indicator, together with other complementary indicators showing the centrality of the air traffic network weighted with the Imported Risk. We implemented our complex network model into an on-line platform which provides the daily risk of expansion of the epidemic to other regions or countries. The platform supports the identification of the components of the network (airports, routes…) that have a major impact on the risk of expansion. The paper also provides findings on how the short-term prediction of diseases' expansion through the Imported Risk indicator allows the identification of effective measures to take control of the virus spread. © ATM 2021. All rights reserved.

COVID-19 Cases Estimation in the UK using Improved SEIR Models

The paper suggests a machine learning algorithm with two modified SEIR models customized for the 2019-nCoV virus and vaccine uses to simulate the spread of COVID-19 in the UK (from Jan 2020 to March 2021) and make predictions of future cases. The algorithm uses COVID daily cumulative case data and second dose vaccine use data provided by the Public Health England as the training set and is capable of making relatively accurate short-term predictions of future COVID cases in the UK (before the delta and later variants of the virus starts spreading within the country). The obtained overall accuracy is above 80% for daily incremental case numbers in terms of the overall fit of the model to real-life data, and with an accuracy of more than 80% for estimation of daily incremental case numbers for 14 days period future prediction. The goal of this paper is to propose improved SEIR models capable of a more accurate simulation for COVID-19 modelling and estimation with various machine learning algorithms. © 2021 IEEE.

Machine learning model of covid-19 forecasting in Ukraine based on the linear regression

Coronavirus or COVID-19 is a widespread pandemic that has affected almost all countries around the globe. The quantity of infected cases and deceased patients has been increasing at a fast pace globally. This virus not only is in charge of infecting billions of people but also affecting the economy of almost the whole world drastically. Thus, detailed studies are required to illustrating the following trend of the COVID-19 to develop proper short-term prediction models for forecasting the number of future cases. Generally, forecasting techniques are be inculcated in order to assist in designing better strategies and as well as making productive decisions. The forecasting techniques assess the situations of the past thereby enabling predictions about the situation in the future would be possible. Moreover, these predictions hopefully lead to preparation against potentially possible consequences and threats. It’s crucial to point out that Forecasting techniques play a vital role in drawing accurate predictions. In this research, we categorize forecasting techniques into different types, including stochastic theory mathematical models and data science/machine learning techniques. In this perspective, it is feasible to generate and develop strategic planning in the public health system to prohibit more deceased cases and managing infected cases. Here, some forecast models based on machine learning are introduced and comprising the Linear Regression model which is assessed for time series prediction of confirmed, deaths, and recovered cases in Ukraine and the globe. It turned out that the Linear Regression model is feasible to implement and reliable in illustrating the trend of COVID-19. © 2021 IEEE.

Bike-Sharing Demand Prediction at Community Level under COVID-19 Using Deep Learning.

An important question in planning and designing bike-sharing services is to support the user's travel demand by allocating bikes at the stations in an efficient and reliable manner which may require accurate short-time demand prediction. This study focuses on the short-term forecasting, 15 min ahead, of the shared bikes demand in Montreal using a deep learning approach. Having a set of bike trips, the study first identifies 6 communities in the bike-sharing network using the Louvain algorithm. Then, four groups of LSTM-based architectures are adopted to predict pickup demand in each community. A univariate ARIMA model is also used to compare results as a benchmark. The historical trip data from 2017 to 2021 are used in addition to the extra inputs of demand related engineered features, weather conditions, and temporal variables. The selected timespan allows predicting bike demand during the COVID-19 pandemic. Results show that the deep learning models significantly outperform the ARIMA one. The hybrid CNN-LSTM achieves the highest prediction accuracy. Furthermore, adding the extra variables improves the model performance regardless of its architecture. Thus, using the hybrid structure enriched with additional input features provides a better insight into the bike demand patterns, in support of bike-sharing operational management.

A Short-Term Prediction Model at the Early Stage of the COVID-19 Pandemic Based on Multisource Urban Data.

The ongoing coronavirus disease 2019 (COVID-19) pandemic spread throughout China and worldwide since it was reported in Wuhan city, China in December 2019. 4 589 526 confirmed cases have been caused by the pandemic of severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), by May 18, 2020. At the early stage of the pandemic, the large-scale mobility of humans accelerated the spread of the pandemic. Rapidly and accurately tracking the population inflow from Wuhan and other cities in Hubei province is especially critical to assess the potential for sustained pandemic transmission in new areas. In this study, we first analyze the impact of related multisource urban data (such as local temperature, relative humidity, air quality, and inflow rate from Hubei province) on daily new confirmed cases at the early stage of the local pandemic transmission. The results show that the early trend of COVID-19 can be explained well by human mobility from Hubei province around the Chinese Lunar New Year. Different from the commonly-used pandemic models based on transmission dynamics, we propose a simple but effective short-term prediction model for COVID-19 cases, considering the human mobility from Hubei province to the target cities. The performance of our proposed model is validated by several major cities in Guangdong province. For cities like Shenzhen and Guangzhou with frequent population flow per day, the values of [Formula: see text] of daily prediction achieve 0.988 and 0.985. The proposed model has provided a reference for decision support of pandemic prevention and control in Shenzhen.

A model based study on the dynamics of COVID-19: Prediction and control.

As there is no vaccination and proper medicine for treatment, the recent pandemic caused by COVID-19 has drawn attention to the strategies of quarantine and other governmental measures, like lockdown, media coverage on social isolation, and improvement of public hygiene, etc to control the disease. The mathematical model can help when these intervention measures are the best strategies for disease control as well as how they might affect the disease dynamics. Motivated by this, in this article, we have formulated a mathematical model introducing a quarantine class and governmental intervention measures to mitigate disease transmission. We study a thorough dynamical behavior of the model in terms of the basic reproduction number. Further, we perform the sensitivity analysis of the essential reproduction number and found that reducing the contact of exposed and susceptible humans is the most critical factor in achieving disease control. To lessen the infected individuals as well as to minimize the cost of implementing government control measures, we formulate an optimal control problem, and optimal control is determined. Finally, we forecast a short-term trend of COVID-19 for the three highly affected states, Maharashtra, Delhi, and Tamil Nadu, in India, and it suggests that the first two states need further monitoring of control measures to reduce the contact of exposed and susceptible humans.