This limitations study quantitatively examining the macro-structure and chronological changes in policy discourse. We applied TF-IDF weighting and LDA Topic Modeling to a corpus of 39 arts-related policy reports published between 2000 and 2024 by nati...
This limitations study quantitatively examining the macro-structure and chronological changes in policy discourse. We applied TF-IDF weighting and LDA Topic Modeling to a corpus of 39 arts-related policy reports published between 2000 and 2024 by national research institutions under the National Research Council for Economics, Humanities and Social Sciences (NRC, 경사연).
The TF-IDF analysis confirmed that the arts policy agenda is multidisciplinary, spanning 13 disparate policy domains including education, legislation, and economy. Key terms such as ‘cooperation,’ ‘exchange,’ ‘fusion,’ ‘regulation,’ and ‘copyright’ demonstrated that the instrumental values of arts have been central issues over the long term, aligning with the trend of instrumental cultural policies linking arts to social structures like the technological development.
advancement LDA Topic Modeling, which yielded an optimal structure of four topics, revealed that Korean arts policy discourse is structured around four distinct axes: Law and Digital Rights, Social Welfare and Regulation, Youth and Regional Development, and Inter-Korean Cultural Exchange. The time-series analysis further demonstrated that policy priorities have historically oscillated between two major driving forces: Geopolitical Specificity, seen in early 2000s concentration on inter-Korean cultural exchange, and Technological Innovation, seen in the prominence of digital rights and legal issues from the 2010s onward.
Our quantitative analysis provides objective, evidence-based insights into the structural evolution of Korean arts policy. It offers critical implications, emphasizing the urgent need for continuous research on the institutional framework for art-tech relationship.
the establishment of permanent inter-ministerial cooperative governance to address complex policy demands, and the adoption of data science methods to build an evidence-based policy system for future-oriented arts policy making.