텍스트마이닝 기반 데이터분석을 통한 전문대학 교양교과에 대한 사회적 담론과 현황이해

Abstract

Objectives The purposes of this study, we seek to gain a macroscopic understanding of the social discourse and current status of liberal arts subjects in colleges in order to improve the quality and strengthen the liberal arts education in colleges.
 Methods To this end, ‘Big data’ was collected using the keywords of ‘junior college+liberal arts’ subjects appearing on the portal site, and data analysis was conducted using the liberal arts subject schedule of junior colleges in the Chungcheong and Gangwon regions as ‘retained data’. Keyword analysis, TF-IDF weight analysis, and network centrality analysis were performed in the big data analysis platform(TEXTOM), and CONCOR analysis was performed using the UCINET6.0 program.
 Results First, as a result of keyword analysis, keywords such as credits, graduation, and completion appeared in portal-collected big data, and in the case of retained data, keywords such as life, English, ability, and understanding were mainly found. Second, keywords with high TF-IDF values a ppeared in the order of ‘credits’, ‘bachelor’s degree’, ‘degree’, and ‘graduation’ in the case of portal-collected big data, and there appeared to be no difference in the case of retained data. Third, as a result of keyword centrality analysis, it was found that in the case of portal big data, ‘credit’ was out of the ranking in closeness centrality, and in the case of retained data, ‘English’ was found to be out of the ranking. Fourth, the clusters formed through CONCOR analysis were found to form two clusters for portal big data and four clusters for retained data.
 Conclusions Big data on liberal arts subjects at colleges showed that social discourse is being formed at a very formal level, such as basic materials related to bachelor's degrees, and the data shows that the nature of liberal arts subjects based on vocational fundamentals is still strong in the composition of subjects.