Abstract
Researchers are able to adopt a text scrapping method to collect data from news articles when data are not available due to privacy protections. This study introduces the processes of text scrapping and analyzing texts of news articles from a local news server in Jeju-do. Since the Jeju government regularly discards the path information of COVID-19 patients, researchers who want to explore characteristics of places where a high number of confirmed cases occurred have predicaments in collecting relevant information. To overcome this challenge for social researchers, this study shows a text analysis process including pre-processing, calculating TF-IDF, creating word clouds, and conducting a word network analysis. The results from analyzing 4500 news articles confirm that there was a serial correlation between the number of daily COVID-19 cases and the number of articles and explore specific features of the places where COVID-19 patients went through. The article would help social researchers to use big data and text mining methods in order to overcome the difficulties of data collection in public administration.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
