• The Journal of Bigdata
• /
• v.1 no.2
• /
• pp.79-89
• /
• 2016

News organizations are looking for a way that can be reused accumulated intellectual property in order to find a new insights. BBC is a worldwide media that continually enhances the value of the news articles by using Linked Data model. Thus, utilizing the Linked Data model, by reusing the stored articles, can significantly improve the value of news articles. In this paper, we conducted a study of Linked Data construction for the healthcare news from a newspaper company. The object names associated with medical description or connected to other published information have been constructed into Linked Open Data service. The results of the study are to systematically organize the news data that were accumulated rashly, and to provide the opportunity to find new insights that could not be found before by connecting to other published information. It may be able to contribute to reused news data. Finally, using SPARQL query language can contribute to interactively searched news data.

• Journal of Digital Convergence
• /
• v.12 no.2
• /
• pp.343-351
• /
• 2014

The present study performed semantic network analysis of the keywords in the headlines of newspapers to investigate the media coverage of the multidrug-resistant microorganisms(MDROs) which is resistant to antibiotics. For this purpose, 229 news stories on MDROs in 28 newspapers from June 1, 2010 to December 31, 2011 were analyzed. The news stories were gathered from the Korea Press Foundation's news database, KINDS (www.kinds.or.kr) and websites of Korean newspapers. The analysis of the keywords revealed 'superbacteria' appeared most frequently (n=155) followed by 'infection' (n=63) which arouses fear among readers. While network was structured with the keywords such as 'domestic', 'multidrug-resistant microorganisms', 'first', 'antibiotics', 'outbreak' and 'infection', the keywords such as 'MDROs related stocks', 'medical staff', and 'safety' were on the periphery of the network.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.171-172
• /
• 2020

본 연구는 오늘날 특수교육의 가장 핵심적인 방법론인 '통합교육'을 다룬 중앙일간지 뉴스 기사의 변화과정을 분석하였다. 신문자료는 오늘날 빅데이터 시대의 하나의 가치 있는 분석대상으로 부각되고 있다. 또 언론사 뉴스 분석방법론은 관련 학문 연구자의 언어가 아닌 일반 시민들의 인식수준을 확인하는 데 도움을 준다. 본 연구의 결과는 2000년 이후 20년간의 시간대를 10년 단위로 분할하여, '통합교육'의 모습이 어떻게 전파되었는 지를 확인하였다. 본 연구는 분석대상 자료를 기초로 하여, 객관적인 연구방법론을 추가하여 보완해 나갈 것이다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2020.07a
• /
• pp.111-114
• /
• 2020

우리나라에 대한 사이버 공격의 배후로 추정되는 북한의 사이버조직에 우리는 얼마나 알고 있을까? 사이버 공간의 특성상 공격 흔적이 남지 않기에 언론사들은 북한의 사이버조직과 관련하여 일관된 정보를 거의 제공하지 못하고 있다. 따라서 갈수록 진화하는 북한의 사이버 공격에 효과적으로 대비하기 위해 본 논문에서는 비록 인터넷에 공개된 자료(논문, 기사 등)라 할지라도 이를 통해서 북한 사이버조직 현황 및 주요 공격사례를 중심으로 관련 정보를 살펴보고자 한다.

• Informatization Policy
• /
• v.25 no.4
• /
• pp.37-64
• /
• 2018

This study aims to forecast the future of the Korean society via a big data analysis. Based upon two sets of database - a collection of 46,000,000 news on 127 media in Naver Portal operated by Naver Corporation and a collection of 70,000 academic papers of social sciences registered in KCI (Korea Citation Index of National Research Foundation) between 2005-2017, 40 most frequently occurring keywords were selected. Next, their temporal variations were traced and compared in terms of number and pattern of frequencies. In addition, core issues of the future were identified through keyword network analysis. In the case of the media news database, such issues as economy, polity or technology turned out to be the top ranked ones. As to the academic paper database, however, top ranking issues are those of feeling, working or living. Referring to the system and life-world conceptual framework suggested by $J{\ddot{u}}rgen$ Habermas, public interest of the future inclines to the matter of 'system' while professional interest of the future leans to that of 'life-world.' Given the disparity of future interest, a 'mismatch paradigm' is proposed as an alternative to social forecasting, which can substitute the existing paradigms based on the ideas of deficiency or deprivation.

• The Journal of the Korea Contents Association
• /
• v.20 no.9
• /
• pp.195-207
• /
• 2020

This study aims to analyze how the Korean liberal and conservative newspapers cover the filibuster for blocking the passage of the anti-terrorism act for the protection of citizens and public security by the main opposition party. For the comparative analysis of the Korean liberal and conservative newspapers, this study analyzes how the newspapers used news frame, news source, key word, and news theme. To analyze the effects on news coverage of the newspapers' ideological orientation, this study selects six newspapers: Hankyoreh Shinmun, Kyunghyang Shinmun, Ohmynews from liberal newspapers and Chosun Ilbo, Donga Ilbo, Joongang Ilbo from conservative newspapers. According to research findings, the liberal and conservative newspapers show clear distinction while using news frames when the newspapers cover the filibuster. The liberal newspapers cover the filibuster as a positive political action while the conservative newspapers cover the filibuster as a negative political action. In addition, as key word, "disturbance" is mentioned most by the conservative newspapers while "poisonous clauses" is used most by the liberal newspapers. As a result, this study shows that newspapers are influenced by ideological orientations while covering political issues.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.78-79
• /
• 2018

최근 가짜뉴스가 무분별하게 확산되면서 가짜뉴스로 인한 경제적, 사회적 비용이 커지고 있다. 하루에 발생하는 가짜뉴스는 방대하며, 실제 뉴스기사를 악의적으로 재생산 또는 언론사를 사칭하는 방식으로 유포되고 있다. 이를 구분하기 위한 연구가 많으나, 공인된 뉴스 기사인지에 대한 신뢰성 입증과 관련된 연구 논문은 매우 적은 상황이다. 본 논문에서는 가짜뉴스 문제를 해결하기 위해 뉴스 플랫폼에 블록체인을 적용, 공인된 뉴스 제공자가 기사 내용에 대한 Fingerprint를 블록체인에 기록하여 공인된 기사 내용에 대한 신뢰성을 검증하는 방안에 대해 제안한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2020.05a
• /
• pp.451-454
• /
• 2020

딥러닝 기술을 이용한 정치적 성향의 편향성 분류를 위하여 신문 뉴스 기사를 수집하고, 머신러닝을 위한 학습 데이터를 구축하였다. 학습 데이터의 구축은 보수 성향과 진보 성향을 대표하는 6개 언론사의 뉴스에서 정치적 성향을 이진 분류 데이터로 구축하였다. 뉴스 기사의 수집 방법으로 최근 이슈들 중에서 정치적 성향과 밀접하게 관련이 있는 키워드 15개를 선정하고 이에 관한 뉴스 기사들을 수집하였다. 그 결과로 11,584개의 학습 및 실험용 데이터를 구축하였으며, 정치적 편향성 분류를 위한 머신러닝 모델을 설계하였다. 머신러닝 기법으로 학습 및 실험을 위해 형태소 단위의 임베딩을 이용하여 문장 및 문서 임베딩으로 확장하였으며, SVM(Support Vector Machine)을 이용하여 정치적 편향성 분류 실험을 수행한 결과로 75%의 정확도를 달성하였다.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.5
• /
• pp.103-110
• /
• 2021

The purpose of this study is to check the trend of press articles and research trends in journal papers in the last 10 years, which dealt with the subject of 'university core competencies' with a big data analysis method. The main research methodology of this study applied the BigKinds analysis system and the semantic network analysis methodology. The results are as follows: First, the number of press articles related to university core competencies showed a keyword trend that rapidly increased in December 2014 and the second half of 2020. Related keywords were curriculum, specialization, project group, Ministry of Education, ACE, and competitiveness. Second, the semantic network value between keywords of related research papers showed 554 degree, 18,467 avg. degree, and 0.637 density. The degree of centrality of connection was analyzed in the order of university(1606), competency(1481), core(1349), and core competency(1301). Betweenness centrality was analyzed as core competencies(13.101), university students(13.101), university(13.101), and competencies(13.101). The results of this research are expected to give implications to future research and policy-making, educational program planning and operation, etc. to members of higher education institutions, experts in education policy, and educational scholars.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.7
• /
• pp.167-173
• /
• 2020

This study aims to analyze the number and trend of news media news through timely analysis of how the articles about airlines and employees show changes before and after Corona19 in the situation where the world economy faces various problems due to the global pandemic of Corona19. For this purpose, the number of articles and trends related to airlines and employees were analyzed and visualized before and after Corona19 using the Korea Press Foundation Bigkinds news analysis service. For this purpose, the Bigkinds service system was extracted from January 1, 2019 to May 31, 2019 and from January 1, 2020 to May 31, 2020. The results of the analysis showed that the number of articles before and after Corona 19 exploded when aviation related events occurred. And it was confirmed that the trend is changing due to the restructuring news. Government and airlines will need to make active efforts to overcome the crisis in the aviation industry due to the impact of Corona 19. The results of this study are significant in that it analyzed the number and trends related to news articles before and after Corona 19, and suggested practical implications for establishing strategies for the future impacts on airlines and employees.