Won Gwang Cho

BACKGROUND: In case of a population-wide infectious disease outbreak, such as the novel coronavirus disease (COVID-19), people's online activities could significantly affect public concerns and health behaviors due to difficulty in accessing credible information from reliable sources, which in turn causes people to seek necessary information on the web. Therefore, measuring and analyzing online health communication and public sentiment is essential for establishing effective and efficient diseas

This study estimates the COVID-19 infection network from actual data and draws on implications for policy and research. Using contact tracing information of 3283 confirmed patients in Seoul metropolitan areas from January 20, 2020 to July 19, 2020, this study created an infection network and analyzed its structural characteristics. The main results are as follows: (i) out-degrees follow an extremely positively skewed distribution; (ii) removing the top nodes on the out-degree significantly decre

This study explored the Korean media's framing of COVID-19 and its impact on people's support for the government. A disaster such as a public health crisis has political consequences. COVID-19 is no exception. However, the direction of the effect is not easily determined. To properly understand this phenomenon, it is necessary to analyze how the media frames the crisis. Using Structural Topic Model, this study examines the Korean media's framing of COVID-19 and especially pays attention to inter

Inappropriate information on a deadly and rare disease can make people vulnerable to problematic decisions, leading to irreversible bad outcomes. This study explored online information exchanges on pancreatic cancer. We collected 35,596 questions and 83,888 answers related to pancreatic cancer from January 1, 2003 to May 31, 2020, from Naver, the most popular Korean web portal. We also collected 8495 news articles related to pancreatic cancer during the same period. The study methods employed we

Emotions that are shared by a large number of people could broadly impact affective experiences at the individual level. Here, we used text mining on popular song lyrics-a cultural product that has been suggested to mirror emotions that many members of a society value and prefer-to track the changes in emotions over time. Morpheme frequency analysis and structural topic modeling on 2,962 hit K-pop songs from 1990 to 2019 showed converging evidence for increased positive emotional content and dec

In this study, we reveal the distinctive communication network structures and contents of online breast cancer community posts in accordance with different cancer stages. Using data collected from community.breastcancer.org, a major online breast cancer community (28,139 original posts and 663,748 replies), we traced the communication network structures and contents of replies associated with its severity. By combining network and quantitative content analyses, we deciphered the functions and ut

이 연구는 메르스와 코로나19 초기 한국 주요 미디어의 보도를 분석함으로써, 한국사회의 감염병 위기 대응에서 나타난 특징과 함의를 탐구한다. 이 연구는 한국에서 메르스 환자 발생 초기와 (2015년 5월 20일 – 6월 23일) 코로나19 환자 발생 초기의 미디어 보도를 (2020년 1월 20일 – 2월 23일) 수집하여 Structural Topic Model 등의 방법을 적용하여 분석하였다. 주요 결과는 다음과 같다. 1) 정치적 입장이 감염병 위기에 대응하는 태도와 관점에 영향을 미치는 것으로 추정된다. 주요 신문들의 감염병 보도량과 주제의 구성이, 해당 매체와 당시 정부의 정치적 성향이 유사한지 아니면 차이나는지에 따라 달라지는 것으로 나타났다. 2) 코로나19에서는 감염병을 최초 발견 지역과 연계하여 설명하는 서사가 메르스에 비해 더 많이 관찰되었다. 한국 사회가 현재, 그리고 향후 감염병 대응에서 부작용을 최소화하며 지혜롭게 대응하기 위해서는, 이런 특징을 참조할 필요가

This study aims to analyze the formation of the frame of breast cancer research. To test our hypothesis that the research frame depends on the funding sources, we collected the abstracts of 48,448 breast cancer research papers from PubMed and applied structural topic modeling, word network analysis, and LASSO logistic regression to the data. In particular, we analyzed the relationship between funding sources and the molecularization of breast cancer knowledge. The results show that government-fu

Abstract This study estimates the COVID-19 infection network from actual data and draws on implications for policy and research. Using contact tracing information of 3,283 confirmed patients in Seoul metropolitan areas from Jan 20 to July 19, 2020, this study creates an infection network and analyzes its structural characteristics. The main results are as follows: (1) out-degrees follow an extremely positively skewed distribution, and (2) removing the top nodes on the out-degree significantly de

Excessive restrictions on individual rights, such as a ban on smartphone use and strict hair regulations, are a major concern among conscripts in South Korea. However, officers often adopt a lukewarm attitude toward their grievances. This study examines whether officers and conscripts have different standards of what is acceptable in the military. Theoretically and empirically, there are systemic differences in how officers and conscripts perform daily tasks; however, we do not have a detailed a

인공 지능 기반 감정 분석은 집합적 감정 분석에 유용하다. 하지만 이제까지의 분석은 주로 데이터를 잘 알려진 몇 가지 감정으로 분류하는 것에 머물렀다. 감정을 둘러싼 이론적 논쟁을 참고하면 이는 감정 분석의 가능성을 제한하는 일이다. 이 글에서는 이런 한계를 넘어서 감정 서사를 포착하는 인공 지능 기반 감정 분석의 가능성을 검토한다. 그 가능성의 핵심에는 셀프-어텐션(self-attention)이 있다. 셀프-어텐션은 트랜스포머 아키텍쳐의 핵심 기술인데, 데이터에서 토큰들 사이의 연결과 의존을 보다 다양하게 포착한다. 그것이 구조 동일성 기반 연결이 아니라 과제 기반 연결에 주목하기 때문이다. 셀프-어텐션에 기반한 다양한 모델을 통해 우리는 감정 서사를 좀 더 정교하게 탐색하는 다양한 전략을 고안할 수 있다. 이 글에서는 자동 문서 생성 인공 지능과 가려진 단어 예측 인공 지능을 활용한 두 가지 전략을 제안한다. 나아가 코로나19 관련 데이터를 활용하여, 자동 문서 생성을 통해 특정

The data used in "Funding sources and breast cancer research frame."