ABSTRACT
During the recent pandemic of COVID-19, an increasing amount of information has been propagated on social media. This situational information is valuable for public authorities. Therefore, this study characterized the propagation scale of situational information types by harnessing the power of natural language processing techniques and machine learning algorithms. We observed that the length of the post has a positive correlation with type 1 information (announcements), and negative words were mostly used in type 5 information (criticizing the government), whereas anxiety-related words have a negative effect on the amount of retweeted type 0 (precautions) and type 2 (donations) information. This type of research study not only contributes to the situational information literature by comprehensively defining categories but also provides data-oriented practical insights into information so that management authorities can formulate response strategies after the pandemic. Our approach is one of its kind and combines Twitter content features, user features and LIWC linguistic features with machine learning algorithms to analyze the propagation scale of situational information, and it achieved 77% accuracy with SVM while classifying the information categories.