Márton, IspányRathi , Bhavesh2024-02-012024-02-012023-11-09https://hdl.handle.net/2437/365973More than 600 million people use the social networking site Twitter worldwide. With the abundance of news viewpoints and data shared by various sources, both public and official, twitter has emerged as a noteworthy platform for accessing health-related information. Currently, twitter serves as a medium for sharing news, exchanging ideas, and discussing global events. The lack of research on languages other than English makes it difficult to find interesting and relevant content in large text streams in different languages. To address this problem, our study looks at a large collection of tweets from nations with a significant number of COVID 19 cases and fatalities. To extract information from this enormous dataset, we use topic identification and sentiment analysis techniques. According to the World Health Organization, COVID 19 is one of the most devastating health pandemics in recent memory and has spread to over 150 countries and territories. In this study, we propose a framework to examine the patterns and progression of behavioral shifts among twitter users during the study period. Our research focuses on 41158 English tweets and aims to shed light on the profound impact of COVID 19. Utilizing three different time intervals, we collect and save connected tweets from the Twitter platform to implement our methodology. Next, we use social network analysis and natural language processing techniques to extract a variety of emotions and corresponding sentiment features from the cleaned and preprocessed dataset. Additionally, the data is displayed to spot any evolving trends. The findings of this study reveal a strong relationship between the emotional traits of twitter users and the infection and fatality rates.53enCovid-19, Machine Learning, Logistic Regression, Twitter, Health IssuesDEENK Témalista::InformatikaHozzáférhető a 2022 decemberi felsőoktatási törvénymódosítás értelmében.