Trend Analysis of Geologic Subdisciplines using a Text-Mining method in South Korea
Abstract
Since the mid-twentieth century, geology in South Korea has gradually evolved with the addition of various study fields as an interdisciplinary context. In the past few decades, there has been little discussion on classifying the geologic subdisciplines latent in a whole geology field and estimating the trend of their evolution over time. In this study, a text-mining method was used with 10,676 articles published in 10 of Korean geological journals from 1968 to 2018 to identify emergence, growth, and diminution topics of geology in South Korea. A latent Dirichlet allocation (LDA) model was employed to classify subdiscipline topics using the text data including paper titles, keywords, and abstracts. Based on the results of LDA, we quantified the annual proportions of each geologic subdiscipline to calculate the popularity index for assessing its rise and fall based on the mean turn point. The result showed that foundational geology involving geochronology, structure geology, stratigraphy, mineral geology and petrology was dominant before 1993. Since 1993, evolutionary geology such as environmental geology, hydrogeology, and engineering geology has emerged, and its proportion has gradually increased. This study provide insight into how geological research topics branch out and merge with other fields. Our result might be useful for researchers and journal editors in geology fields to understand the relations among the various subdisciplines of geological research in South Korea.
- Publication:
-
AGU Fall Meeting Abstracts
- Pub Date:
- December 2020
- Bibcode:
- 2020AGUFMIN0140004K
- Keywords:
-
- 1920 Emerging informatics technologies;
- INFORMATICS;
- 1938 Knowledge representation and knowledge bases;
- INFORMATICS;
- 1954 Natural language processing;
- INFORMATICS;
- 1958 Ontologies;
- INFORMATICS