토픽모델링과 의미네트워크분석을 이용한 설교내용 분석: Y교회 L목사 2016년 설교를 중심으로

Advances in text mining based on machine learning and natural language processing have made it possible to analyze large amounts of big data. Prior to text mining, qualitative research studying topic modeling like content analysis manually has been a time-consuming, but with the development of text mining, we can perform efficiently qualitative research using unstructured data by automated methods. Therefore, the purpose of this study is to suggest a method that can shorten the time to analyze sermon contents by using text mining method. To this end, the scope of this study was based on the 10-month preaching of Rev. L, a large church, in 2016. Using text mining-based topic modeling and semantic network analysis, this study examined word frequency, sermon topics, and words centrality used in the sermon and then proposed a methodology for analyzing identification and trend of key words. The significance of this study is that it is a research methodology that combines quantitative methods with existing qualitative methods, as well as an alternative that can reduce the time to analyze sermon contents.