Investigating dynamic relations between factual information and misinformation: Empirical studies of tweets related to prevention measures during COVID-19

During COVID-19, misinformation on social media has affected people's adoption of appropriate prevention behaviors. Although an array of approaches have been proposed to suppress misinformation, few have investigated the role of disseminating factual information during crises. None has examined its effect on suppressing misinformation quantitatively using longitudinal social media data. Therefore, this study investigates the temporal correlations between factual information and misinformation, and intends to answer whether previously predominant factual information can suppress misinformation. It focuses on two prevention measures, that is, wearing masks and social distancing, using tweets collected from April 3 to June 30, 2020, in the United States. We trained support vector machine classifiers to retrieve relevant tweets and classify tweets containing factual information and misinformation for each topic concerning the prevention measures' effects. Based on cross-correlation analyses of factual and misinformation time series for both topics, we find that the previously predominant factual information leads the decrease of misinformation (i.e., suppression) with a time lag. The research findings provide empirical understandings of dynamic relations between misinformation and factual information in complex online environments and suggest practical strategies for future misinformation management during crises and emergencies. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Novel Approach for Predicting COVID-19 Symptoms using ARM based APRIORI Algorithm

Based on several pre-defined standard symptoms, a model that can determine the coronavirus illness as positive is developed. Guidelines for these symptoms have been issued by the World Health Organization (WHO) and India's Ministry of Health and Family Welfare. In this model the various symptoms of the illnesses is given to the system. It allows users to discuss their symptoms, with the algorithm predicting a condition based on factual information. This factual information is then evaluated using the ARM based Apriori algorithm to get the most accurate results. Other conventional models such as Support Vector Machine (SVM), Artificial Neural Networks (ANNs), and Random Forests (RF) are considered and have analyzed the predictions and have found that the proposed algorithm predicts a higher accuracy score. © 2022 IEEE.