Sentiment Analysis of Covid-19 Tweets using Twitter Database-A Global Scenario

Sentiment analysis falls within the category of Natural Language Processing (NLP) technology. Behaviour analysis and recommendation employ sentiment analysis. On the dataset of COVID-19 tweets, random forest Classifier, Decision Tree, Support Vector Machine (SVM), and Random Forest are the machine learning methods under consideration for sentiment analysis. The total number of tweets used for this research is 179108. Pre-Processing is used to clean and analyze these tweets. The sentiment analysis of COVID-19 tweets used in this study reveals the individual experiences of those affected by the epidemic. The primary goal of this survey is to analyze people's experiences. It helps to better understand the emotions of people, especially during an epidemic period. Twitter, a microblogging platform, contains a sizable collection of datasets that illustrate a wide range of human emotions, including fear, happy, sad, anger, and joy etc. Sentiment analysis is crucial for gauging the consensus of the populace. This research can help us assess the potential impact of a pandemic on the general public's decision-making. © 2022 IEEE.

Analysing the educational challenges during Covid-19 by using R-programming

In today's world, Education is considered one of the important fields. Especially during Covid-19's epidemic, it is necessary to explore online teaching learning. Institutions, Educators and Learners are unpredictably accepting the remote teaching learning. This research paper check the influence of remote teaching methodologies in the midst of the epidemic and find the feelings of Educators and Learners during the classes that are available online. Based on the research aim the questionnaire framed and distributed to Educators and Learners through Social Media. The data's were collected and classified with the help of Statistical Analysis using R-Programming the results were obtained. The Educators and Learners both were satisfied new modern teaching learning method.

Binding Interaction Analysis of Phytoconstituents Of Commiphora mukul With 3CLPro And PLPro Enzymes Of SARS-CoV-2 Virus

The SARS-CoV-2 belongs to a family of coronaviruses, responsible for the covid-19 pandemic. The Chymotrypsin-like protease (3CLpro) and Papain-like protease (PLPro), two important enzymes of the SARSCoV-2 play a key role in translating the viral RNA genome into functional proteins. This study aimed to evaluate and analyse the binding interactions of phytochemicals of oleoresin of Commiphora mukul plant with 3CLPro and PLPro enzymes of SARS-CoV-2 virus. Docking studies were performed on 3CLPro and PLPro with 30 phytoconstituents using AutoDock Vina. A total of 12 compounds were shortlisted based on their minimum binding energies. Their minimum binding energy ranged from -9.2 to -7.1 kcal and the analysis and interpretations are tabulated. Further, the ADME, drug-likeness, and bioactivity scores were documented. The current study enlightened the binding abilities, and the interactions of constituents present in the oleoresin of Commiphora mukul plant with the active sites of 3CLPro and PLPro enzymes. © The Electrochemical Society

Forecasting Diurnal Covid-19 Cases for Top-5 Countries Using Various Time-series Forecasting Algorithms

On January 30, 2020, the World Health Organisation classified the Covid-19 outbreak a Public Health Emergency of International Concern, and a pandemic was proclaimed on March 11, 2020. Two years after the Covid-19 outbreak, the virus has new transmutations plus is turning out to be more difficult for forecasting in terms of both its behaviour and severity. Various techniques for time series analysis of coronavirus (Covid-19) cases were examined in this study. The Deep Learning model chosen, Long Short-Term Memory (LSTM) is compared against Statistical approaches, such as Linear Regression, Auto-Regressive Integrated Moving Average (ARIMA), and Seasonal Auto-Regressive Integrated Moving Average (SARIMA), based on a variety of performance metrics. Following the estimates of the superior algorithm, medical care professionals can act at the appropriate moment to supply Equipment to health care institutions and further help the public. According to our data, as the number of projected days grows, so does the model's error rate. Forecasted trends also suggest that statistical approaches are relatively better overall for predictions of fewer days, but Deep Learning methods are relatively better for forecasts of more days. © 2022 IEEE.

Ai based personalized healthcare application to keep up the well-being of people by boost the immunity through food and physical activity during pandemic

In recent times Covid-19, a worldwide pandemic affecting people globally. As on August 31, 2020 more than 25,118,689 cases were confirmed worldwide. In India 3,621,245 confirmed cases with 64,469 deaths were reported. Epidemiological specialistssuggest that the spreading of the virus can be controlled only by imposing quarantine status (i.eself-Isolation, self-quarantine, maintain socialdistancing and home confinement) for the majority of the population. During pandemic situation all the public activities are depressed. The prolonged closure and home confinement during a disease outbreak might have negative impact not only on the people’s physical health but also on their and mental health too.There exists a direct associationamong diet, physical activity, and healthof the citizen. To keep up the wellbeing of the people and for preventing other kinds of diseases there is a need to maintain both their physical and mental health. An adequate, well balanced diet combined with regular physical activity is thebase for good health. Poor nutrition can lead to reduced immunity, increased susceptibility to various diseases, damage the physical and mental health of the people, and reduced their productivity.In this paper, an AI based personalized healthcare application is designed and develop tosuggest suitable nutrients through food to improve their immunity for all categories of people based on their age and health condition and to teach simple exercises and yoga asanato strengthen both physical and mental health of the citizen.The information is gathered from the domain experts to create a knowledge base. Knowledge base also interfaces with the pre-built system for authorized procedure for diagnosis, treatment process, condition-specific guidelines, and promoting the use of best practice with the help of experts. Personalized medication is suggested based on the inferences derived from the engine.Details of every person are stored regularly in terms of different facts.These would help us to derive the decisions and provide suggestions to the people in a consistent way.Machine learning algorithms are used to learn data patterns and derive relevant insights as inferences that would be helpful in treating the people in a healthier way.Personalized Health dashboard capture real-time data and analyze data patterns effectively. It would produce precise and timely report following government standards that help in improving patients’ health. The Application give recommendation related to the kind of food that can be taken for improving immunity based on their health and give simple exercises to improve their health system during any kind of pandemics. © 2021, Universitatea de Vest Vasile Goldis din Arad. All rights reserved.