• The Journal of the Korea Contents Association
• /
• v.20 no.5
• /
• pp.118-127
• /
• 2020

The paper introduces trends and methodological challenges of quantitative Korean text analysis by using the case studies of academic and news media articles on "migration" and "immigration" within the periods of 2017-2019. The quantitative text analysis based on natural language processing technology (NLP) and this became an essential tool for social science. It is a part of data science that converts documents into structured data and performs hypothesis discovery and verification as the data and visualize data. Furthermore, we examed the commonly applied social scientific statistical models of quantitative text analysis by using Natural Language Processing (NLP) with R programming and Quanteda.

• The Journal of the Korea Contents Association
• /
• v.22 no.8
• /
• pp.94-105
• /
• 2022

The purpose of this study is to suggest improvement plan for a commentary on figure skating in Korea from comparing to NBCSN and MBC's coverage of the 2018 Pyungchang Olympic Games employing both of quantitative and text analysis. Results indicate that NBCSN and MBC's commentary on figure skating have definitely different characteristics in terms of expertise and dramatizing ability. The commentator of MBC frequently used monotonous and repetitive emotional expression and provided incoherent information in very automatic way. Whereas, NBCSN's comments expressed very diverse way on introduction of players, explanation of technique and evaluation, especially on dramatizing ability to contextualize combining players' performance and background information.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.4
• /
• pp.549-566
• /
• 2022

Recently, artificial intelligence (AI) technology has progressed rapidly, and industries using this technology are significantly increasing. Further, analysis research using text mining, which is an application of artificial intelligence, is being actively developed in the field of social science research. About 125 laws, including joint laws, have been enacted under the Ministry of Oceans and Fisheries in various sectors including marine environment, fisheries, ships, fishing villages, ports, etc. Research on the laws under the Ministry of Oceans and Fisheries has been progressively conducted, and is steadily increasing quantitatively. In this study, the domestic research trends were analyzed through text mining, targeting the research papers related to laws of the Ministry of Oceans and Fisheries. As part of this research method, first, topic modeling which is a type of text mining was performed to identify potential topics. Second, co-occurrence network analysis was performed, focusing on the keywords in the research papers dealing with specific laws to derive the key themes covered. Finally, author network analysis was performed to explore social networks among authors. The results showed that key topics have been changed by period, and subjects were explored by targeting Ship Safety Law, Marine Environment Management Law, Fisheries Law, etc. Furthermore, in this study, core researchers were selected based on author network analysis, and the tendency for joint research performed by authors was identified. Through this study, changes in the topics for research related to the laws of the Ministry of Oceans and Fisheries were identified up to date, and it is expected that future research topics will be further diversified, and there will be growth of quantitative and qualitative research in the field of oceans and fisheries.

• Tunnel and Underground Space
• /
• v.25 no.4
• /
• pp.303-319
• /
• 2015

Text mining is one of the branches of data mining and is used to find any meaningful information from the large amount of text. In this study, we analyzed titles and keywords of two SCI journals on rock engineering by using text mining to find major research area, trend and associations of research fields. Visualization of the results was also included for the intuitive understanding of the results. Two journals showed similar research fields but different patterns in the associations among research fields. IJRMMS showed simple network, that is one big group based on the keyword 'rock' with a few small groups. On the other hand, RMRE showed a complex network among various medium groups. Trend analysis by clustering and linear regression of keyword - year frequency matrix provided that most of the keywords increased in number as time goes by except a few descending keywords.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.655-667
• /
• 2014

This paper has identified five major categories of the T2D patients' concerns based on an online forum where the patients voluntarily verbalized their naturally occurring emotional reactions and concerns related to T2D. We have emphasized the fact that the lexical and phrasal analysis brought to the forefront the prevailing negative reactions and desires for clear information, professional advice, and emotional support. This study used lexical and phrasal analysis based on text-mining tools to estimate the potential of using a large sample of patient conversation of a specific disease posted on the internet for clinical features and patients' emotions. As a result, the study showed that quantitative analysis based on text-mining is a viable method of generalizing the psychological concerns and features of T2D patients.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2010.11a
• /
• pp.189-192
• /
• 2010

분자 생물학을 통한 연구가 심화되면서, 생물학 정보는 기하급수적으로 늘어나고 있다. 그에 따라 바이오메디컬(생물학, 의학) 관련 논문들의 출판 및 등록 건수도 해마다 증가하고 있다. 그러나 바이오메디컬 문서들에서 유용한 정보를 추출하는 기술은 이러한 분야의 전문가 큐레이터(curator)에 의존한 경우가 많아서, 그 작업의 속도와 양적인 면에서 한계를 가지고 있다. 이러한 이유 때문에 바이오메디컬 문서를 기계학습을 통하여 분석하는 기법이 도입되기 시작하였다. 아직까지는 기계학습을 이용하여 구축된 데이터베이스가 소수에 불과하지만, 점차 증가하는 추세에 있다. 이러한 현 추이를 분석하고 향후의 추세를 예측하고자 텍스트마이닝 기술이 생물학과 의학 분야에서 어떻게 사용되며, 그 정보들이 어떻게 관리되는지 연구, 조사 하게 되었다. 현재 바이오메디컬 관련 데이터베이스들이 여러 기관 및 단체에 의해 구축 및 관리되고 있으며, 국가적인 프로젝트로서 이러한 데이터베이스들을 통합하는 과정을 진행하고 있다. 이처럼 국가기관의 주도하에 데이터베이스를 통합하여 관리하고자 하는 노력들이 계속되고 있어, 앞으로는 바이오메디컬 자료들을 검색하기가 보다 용이해질 것으로 생각된다. 텍스트마이닝을 이용하여 바이오메디컬 정보들을 추출하는 기술은 초기에는 공동 발생(co-occurence)과 같이 단순한 통계적 방법을 이용하였지만, 최근에는 다른 문서에서 추출된 정보와 기존의 정보들을 연계하여 새로운 정보를 추출해 내는 기법이 확산되고 있음을 알 수 있었다.

• Journal of vocational education research
• /
• v.33 no.3
• /
• pp.83-104
• /
• 2014

The study examined the trends of research on Meister high schools in Korea. The study also investigated differences of research interests between the university faculty and graduate students who are the future researchers in this field. A total of 56 research articles were analyzed using the network text analysis method and the content analysis. The results showed that 56% of all studies was done to reveal the distinguishable characteristics of Meister students and teachers compared to their counterpart in vocational schools. 17.6% of studies were about school curriculum, while 14.0% of studies were on school organization and operation. Only 12.3% of studies were conducted to evaluate school performance. Quantitative studies outnumbered qualitative ones. Based on the results, this study suggested implications for policies and future research on meister high school.

• The Journal of the Korea Contents Association
• /
• v.12 no.1
• /
• pp.176-184
• /
• 2012

People are exposed to various media. After the Digital Revolution, quantitative expansion of the media is at a rapid pace. Because of the expansion of the media, advertising needs efforts that induce the audiences' reaction. Rhetorical devices are used as the efforts. This study noted the visual paradox of rhetorical devices because it is an effective representation device that induced audiences' reaction by deliberate contradiction and ambiguity. This study has defined the visual paradox based on define and classification of paradox in logic. This study also tried to reveal the relationship between images and text for signification by metalanguage because it is important to the visual paradox in advertising. And analyzed cases of Volkswagen ads to prove the research process. Finally identified that images and text interact to create a new meaning.

• The Korean Journal of Applied Statistics
• /
• v.29 no.6
• /
• pp.1007-1023
• /
• 2016

This paper explores the conditions and potential of newly designed and tried methodology of big data analysis that apply to Korean history subject matter. In order to advance them, we need to pay more attention to quantitative analysis methodologies over pre-existing qualitative analysis. To obtain our new challenge, I propose 'digital history' methods along with associated disciplines such as linguistics and computer science, data science and statistics, and visualization techniques. As one example, I apply interdisciplinary convergence approaches to the principle and mechanism of elite reproduction during the Korean medieval age. I propose how to compensate for a lack of historical material by applying a semi-supervised learning method, how to create a database that utilizes text-mining techniques, how to analyze quantitative data with statistical methods, and how to indicate analytical outcomes with intuitive visualization.

• The Journal of the Korea Contents Association
• /
• v.21 no.12
• /
• pp.816-827
• /
• 2021

The purpose of this study is to understand the relationship between fear and anger emotions in the discourse produced by the media during the period of major emerging infectious diseases (SARS, Swine Flu, MERS, and COVID-19) that occurred since 2000 in Korea. The researcher collected editorial articles of the major daily newspaper after a significant epidemic of new infectious diseases and analyzed them using the Extended Parallel Processing Model (EPPM) and text mining techniques. In all epidemic times, fear appears stronger than anger, but the smaller the fear, the greater the risk control message is produced. In detail, fear emerges strongly in the discourse of the risk of infectious diseases or the economic crisis. Anger appears strong when the government's quarantine failures, groups where group infections occurred, and concealing information about infectious diseases. In this process, anger is strongly expressed against the factors that threaten the safety of society. Anger is also an emotion that can justify strong quarantine, but it can be the basis for discourse on minority hate. In this respect, anger is a two-sided emotion, so it must be handled carefully in the media.