• International Journal of Computer Science & Network Security
• /
• 제24권6호
• /
• pp.1-7
• /
• 2024

Comparing text features involves evaluating the "similarity" between texts. It is crucial to use appropriate similarity measures when comparing similarities. This study utilized various techniques to assess the similarities between newspaper articles, including deep learning and a previously proposed method: a combination of Pointwise Mutual Information (PMI) and Word Pair Matching (WPM), denoted as PMI+WPM. For performance comparison, law data from medical research in Japan were utilized as validation data in evaluating the PMI+WPM method. The distribution of similarities in text data varies depending on the evaluation technique and genre, as revealed by the comparative analysis. For newspaper data, non-deep learning methods demonstrated better similarity evaluation accuracy than deep learning methods. Additionally, evaluating similarities in law data is more challenging than in newspaper articles. Despite deep learning being the prevalent method for evaluating textual similarities, this study demonstrates that non-deep learning methods can be effective regarding Japanese-based texts.

• Journal of Preventive Medicine and Public Health
• /
• 제36권3호
• /
• pp.298-301
• /
• 2003

Objectives : There is an increasing concern for the social, economic, environmental and health effects of the Asian dust (Hwang-sa in Korean language) in Korea. In this study, we intended to indirectly determine ordinary people's perception about the Asian dust by analyzing the contents of newspaper articles dealing with it. Methods: By using article searching services in the internet websites of three newspaper companies, we collected newspaper articles dealing with the Asian dust during the period from January $1^{st}$ of 1998 to December $31^{st}$ of 2002. We classified the articles into four categories: those forecasting the occurrence of the Asian dust, those about measures to cope with it, those about its occurrence in the neighboring foreign countries, and those about its effects. In particular, we analyzed articles about the health effects of the Asian dust more distinctly. Results : A total of 1,225 articles dealing with the Asian dust were found during the 5 year period. The number of articles increased from 102 in 1998 to 518 in 2002, approximately a five-fold increase, The numbers of articles about health effects, environmental effects and economical effects were 191 (44%), 171 (41%) and 147 (34%), respectively. It was reported that various diseases such as respiratory diseases (87%), eye problems (69%), and skin diseases (12%) were associated with the Asian dust. Conclusion : The increasing concern for the negative effects of the Asian dust necessitates more studios about this field. As the effects of the Asian dust are various, the information on the major concern of ordinary people could help establish the research agendas and measures for the Asian dust.

• 디지털융복합연구
• /
• 제20권1호
• /
• pp.1-13
• /
• 2022

본 연구에서는 미세먼지에 대한 신문 기사의 시대별, 신문사별 특징을 살펴보고 있다. 이를 위하여 빅카인즈에서 1995년 이후 주요 신문사들의 관련 기사를 추출하였고 텍스트마이닝, 감성분석, 회귀분석을 활용하였다. 그 결과, 2010년 이전에는 대기오염도 측정 단어나 국내 오염원 관련 단어가 많이 등장했으나 2010년대에 들어서면서 "중국"이 큰 빈도로 나타났으며 정책적 대응, 미세먼지가 건강에 미치는 영향, 관련 제품에 대한 광고·홍보, 국내 오염원에 관한 기사까지 다양한 주제의 기사가 등장했다. 중앙일보, 한겨레, 경향신문은 상대적으로 정부의 정책이나 규제와 관련된 기사가 많은 반면, 대부분의 지역지에서는 지역 자체의 배출원 및 저감대책에 관한 기사가 많았다. 본 연구 결과는 미세먼지 관련 언론보도의 추이를 살필 수 있는 기초 자료로 활용될 수 있으리라 기대한다. 향후 포스트코로나 시대의 국내 미세먼지의 상황과 관련 기사의 트렌드를 추가적으로 비교, 검토할 수 있을 것이다.

• 한국문헌정보학회지
• /
• 제46권1호
• /
• pp.223-240
• /
• 2012

본 연구는 은평구립도서관의 신문기사 분석사례를 통해 신문기사를 통한 공공도서관의 홍보의 실태를 살펴보고 이해하는데 목적이 있다. 이를 위해 본 논문은 신문기사를 통한 공공도서관의 홍보에 대한 이론적 배경을 살펴 본 후, 은평구립도서관과 관련된 2010년도 신문기사를 기사유형, 기사종류, 기사성격, 기사내용 등으로 나누어 살펴보았다. 또한 본 탐색적 사례연구는 내용분석, 면담, 현장방문 등을 통하여 은평구립도서관과 관련된 2010년도 신문기사를 홍보주체, 홍보대상, 홍보방향, 그리고 홍보방법 등 공공도서관의 홍보에 영향을 미치는 요소들을 중심으로 분석하였다.

• Journal of information and communication convergence engineering
• /
• 제18권4호
• /
• pp.216-221
• /
• 2020

Artificial intelligence (AI), an essential skill of the Fourth Industrial Revolution, is being actively taught in higher education; however, AI education is only in the preparatory stage in elementary, middle, and high schools. Investigating various newspaper articles related to AI education to date can aid in basic data collection, which is an important process in the preparatory stage. Accordingly, 13,378 newspaper articles were collected from a total of 21 newspapers, and five topics were extracted using the latent Dirichlet allocation (LDA)-based topic model along with frequency analysis. Newspaper articles from the early 2000s expanded to technologies related to the Fourth Industrial Revolution. Accordingly, education in AI fields should be linked with education in AI-based technology. In addition, efforts should be made to secure the continuity and sequence of AI education in cooperation with related higher institutions and companies.

• 의학교육논단
• /
• 제24권2호
• /
• pp.103-112
• /
• 2022

The purpose of this study was to explore, using topic modeling, the social value of doctors and medicine demanded by society as reflected in published newspaper articles in Korea. Ultimately, this study aimed to reflect social needs in the process of developing the Patient-Centered Doctor's Competency Framework in Korea. For this purpose, a total of 2,068 newspaper articles published from 2016 to 2020 were analyzed. Through topic modeling of these newspaper articles over the past 5 years, 18 topics were derived and divided into four categories. Focusing on the derived topics and keywords, the topics derived in specific years and the proportion of topics by year were analyzed. The results of this study make it possible to grasp the needs of society projected through the press for doctors and medicine. Due to the nature of the press, topics that frequently appeared in newspaper articles were mainly social phenomena related to requirements for doctors, particularly dealing with economic and legal aspects. In particular, it was confirmed that doctors are now required to have a wider range of competencies that go beyond their required medical knowledge and clinical skills. This study helped to establish doctor's competencies by analyzing social needs for doctors through the latest research methods, and the findings could help to establish and improve doctor's competencies through ongoing research in the future.

• 한국식생활문화학회지
• /
• 제21권3호
• /
• pp.233-240
• /
• 2006

This study was intended to help children to cultivate and develop a sound attitude toward food consumption and eating habits through the analysis of food and nutritional information in news articles and advertisements in three major daily children's newspapers in Korea: The Chosen Children's Daily Newspaper, The Hankook Children's Daily Newspaper, and The Donga Children's Daily Newspaper. The monitoring period was for twelve months, January to December 2003. Two hundred seventy-nine articles and three hundred thirty-five advertisements were analyzed. The results were as follows. 'Cooking and health' were the most frequent subject in food and nutrition articles. The articles' contents are evaluated positively in morality and explanation; but negatively in fairness, specialization, and objectiveness. The articles were insufficient in the explanation of professional terms, scientific bases, and practical measures for real life. It therefore seems that they were difficult for children to understand well. The most frequent themes in the advertisements were 'processed fats and sugars' such as chocolate, candies, and cookies. Frequently, they were exaggerated and accompanied by phrases promoting consumption. They did not provide sufficient well-grounded information, and focused too much on events or gifts to instigate consumer sentiment. In conclusion, the most serious problem was that most food and nutrition information in these children's newspapers was lacking in specialization. More specialized and objective information should be provided in order to enhance the educational value of children's newspapers and their utilization in school education programs. Continuous monitoring should be carried out to discover those news articles and advertisements that contain correct food and nutrition information.

• 한국산학기술학회논문지
• /
• 제22권6호
• /
• pp.375-384
• /
• 2021

본 연구는 조현병 관련 기사에 나타난 키워드와 주요 주제의 변화를 파악하는 의미연결망 분석, 계량적 내용분석 연구이다. 연구대상은 강남역 살인사건 전후 5년간 보도된 조현병 관련 신문기사이다. 수집된 자료는 NetMiner 프로그램 4.4.1을 이용하여 네트워크 통계분석을 시행하였다. 2013년부터 2018년까지 8개 중앙지에서 610개의 신문기사가 검색되었다. 출현빈도가 가장 높은 주요 키워드는 강남역 살인사건 이전에는 '치료', 사건 이후에는 '사건'으로 나타났다. 사건 이전에는 '편견으로 치료시기를 놓치면 만성화 됨', '조기 치료하면 치료가 가능함', '약물치료로 정상적인 생활이 가능함', '심신미약 상태에서 살인 혐의로 기소됨'이라는 네 가지 주제가 도출되었다. 반면, 사건 이후 '여성혐오주의자가 아니라 피해망상이 심해져 살인을 저지름', '약물치료 중단으로 충동적인 행동이 유발됨', '범행 후 심신미약으로 인한 감형을 주장함', '흉기 난동에 출동한 경찰을 살해함'이라는 네 가지 주제가 도출되었다. 이러한 결과는 신문기사가 조현병 및 기타 정신질환자에 대한 편견과 낙인을 줄이기 위해 조현병에 대한 정확한 정보를 제공해야 함을 시사한다.

• 무역학회지
• /
• 제46권4호
• /
• pp.61-76
• /
• 2021

This study focuses on three logistics-related news (Logistics Newspaper, Korea Shipping Gadget, and Korea Shipping Newspaper) in order to present changes in logistics issues, centering on Corona 19, which has recently had the greatest impact in the world. For data collection, two-year news articles in 2019 and 2020 (title, article, content, date, article classification, article URL) were collected through web crawling (using Python's BeautifulSoup, requests module) on the homepages of three representative logistics-related media companies. As for the data analysis methods, fundamental statistical analysis, Latent Dirichlet Allocation (LDA) for topic modeling, and Scattertext were performed. The analysis results were as follows. First, among the three news media related to logistics, the Korea Shipping Newspaper was carrying out the most active media activities. Second, through topic modeling with LDA, eight logistics-related topics were identified, and keywords and significant issues of each topic were presented. Third, the keywords were visually expressed through Scattertext. This is the first study to present changes in the logistics field, focusing on articles from representative logistics-related media in 2019 and 2020. In particular, 2019 and 2020 can be divided into before and after the outbreak of Corona 19, which has had a great impact not only on the logistics field but also on our lives as a whole. For future work, a multi-faceted approach is required, such as comparative studies of logistics issues between countries or presenting implications based on long-term time-series articles.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권10호
• /
• pp.731-738
• /
• 2013

본 논문은 사회의 최근 동향에 대한 여론의 반응을 관찰하기 위한 방법을 나타낸다. 최근 동향을 나타내는 키워드를 신문기사로부터 추출하고, 추출된 키워드를 이용하여 수집된 트윗의 감성 분석을 통해 최근 동향에 대한 여론을 분석한다. 수집된 신문기사를 k-means알고리즘을 이용하여 군집화하고, 군집내의 단어의 출현 빈도를 이용하여 토픽 키워드를 선정하였다. 각 토픽에 대하여 수집된 트윗은 그 토픽 대한 트윗이라는 가정하에 기계학습 방법을 이용하여 긍/부정을 판별하여 감성을 판단하게 하였다. 그리고 이와 같은 가정에 대한 타당성을 검증해 보았다.