• Title/Summary/Keyword: 신문기사 분석

Search Result 362, Processing Time 0.023 seconds

Content Analysis of Newspapaer Articles on Divorce(II) - Focusing on Chosun and Donga from the 1940's to 1990's - (신문기사를 통해 본 이혼 양상에 대한 내용분석(II) - $1940\~1990$년대 조선$\cdot$동아일보를 중심으로)

  • Lee, Kang-Yi;Choi, Hea-Young
    • Journal of the Korean Home Economics Association
    • /
    • v.43 no.9 s.211
    • /
    • pp.129-141
    • /
    • 2005
  • In this study, the major tendencies of divorce as represented in articles of Korea's major daily newspapers from the 1940's to the 1990's were explored. The method used for this study was content analysis, and 1,741 articles related to divorce were selected for analysis from the Chosun and Donga. The main categories and subcategories were classified as attitude toward divorce(negative, accepting, neutral), present condition of divorce(statistics, survey, analysis), cause of divorce(marital conflict, conflict with family, health-related troubles, financial troubles, and others), and information offered about divorce(related-laws, prevention and adaptation, and others). The major findings of this study were as follows. 1) The most frequently found category was information offered about divorce, and the following categories were featured in the newspapers in the order of cause of divorce, present condition of divorce, and attitude toward divorce. 2) The major discussions of divorce as represented in articles of Korea's daily newspapers from the 1940's to 1990's have been reflecting the changes of related laws, policy and legislation in our society. 3) The content analysis of newspaper articles on divorce indicated that concepts of marriage, divorce and family in our society have been diversified.

Implement of Relevance Feedback in "MIRINE" Information Retrieval System ("미리내" 정보검색 시스템에서 Relevance Feedback 구현)

  • Park, Su-Hyun;Park, Se-Jin;Kwon, Hyuk-Chul
    • Annual Conference on Human and Language Technology
    • /
    • 1997.10a
    • /
    • pp.65-71
    • /
    • 1997
  • 이 논문은 부산대학교 전자계산학과 인공지능 연구실에서 개발한 정보검색 시스템 "미리내"의 적합성 피드백 방법을 분석하고, 그 방법들의 검색 효율을 비교 분석하였다. "미리내"에서 질의문은 자연언어 질의문을 사용하고 재검색을 위한 적합성 피드백은 원질의문에서 검색된 문서 중 이용자가 직접 선택한 적합 문서에서 추출한다. 적합성 피드백은 크게 단어 확장(Term Expansion)을 위한 단어 선택 방법과 추가될 단어에 가중치를 부여하는 단어 가중치 부여(Term Weighting)의 2가지 요소로 이루어진다. 단어 선택을 위해서는 적합 문서에 나타난 단어 빈도합(tf), 역문헌빈도(idf), 적합 문서 중에서 해당 단어가 있는 적합 문서의 비율(r/R) 등의 정보를 이용한다. 단어 가중치 부여 방법으로는 정규화 또는 코사인 함수를 이용하여 부여하였다. 단어확장에는 tfidf가 tfidf(r/R)보다 정확도 면에서 나은 향상율을 보였으나, 30위 내 검색된 적합문서의 수를 비교해 보았을 때 tfidf(r/R)의 정확도가 높았다. 단어 선택 방법에서 계산된 값을 정규화하여 가중치를 부여하였을 때 보다 코사인 함수를 이용하여 가중치를 부여하였을 때 정확도가 높았다. 실험은 KT-Set 2.0 (4391 건), 동아일보 96 년 신문기사(70459 건)를 대상으로 수행하였다.

  • PDF

The Content Analysis of Newspaper Articles on Divorce -Focusing on Choseun ilbo and Donga ilbo in the 1920′s and 1930′s - (신문기사를 통해 본 이혼 양상에 대한 내용분석(I) - 1920∼1930년대 조선ㆍ동아일보를 중심으로 -)

  • Lee Kangyi;Choi Heayoung
    • Journal of the Korean Home Economics Association
    • /
    • v.42 no.11
    • /
    • pp.47-60
    • /
    • 2004
  • In this study, the major tendencies of divorce as represented in articles of Korea's daily newspapers in the 1920's and 1930's were explored. The method used for this study was content analysis, and 432 articles related to divorce were selected for analysis from Choseun and Donga ilbo. The main categories and subcategories were classified as attitude toward divorce(negative, acceptive, neutral), present condition of divorce(statistics, suvey, analysis), cause of divorce(marital conflict, conflict with family, health-related troubles, financial troubles, and the others), and information offered about divorce(related-laws, prevention & adaptation, and the others). The major findings of this study were as follows. 1) The most frequently found category was the cause of divorce(given in 47.5% of the total articles), and especially noticeable was an increase of marital conflict. 2) In the case of attitude toward divorce(12.5%), percentiles of negative, acceptive, and neutral attitudes appeared nearly similarly, which is a representation of the transitional tendency of those times. 3) In the 1930's, information offering articles(25.2%) increased quantitatively as well as qualitatively compared with the 1920's.

A Study on the Applicability of 2-Poisson Model for Selecting Korean Subject Words (2-포아송 모형을 이용한 한글 주제어 선정에 관한 연구)

  • 정영미;최대식
    • Journal of the Korean Society for information Management
    • /
    • v.17 no.1
    • /
    • pp.129-148
    • /
    • 2000
  • Experiments were performed on three subsets of a Korean test collection in order to determine whether 2-Poisson model's Z value is a good measure for selecting subject words from a document to be indexed. It was found that subject word selection based on the Z value was effective for only one subset with short texts, i.e., the Science and Technology subset. Correlation analyses between 2-Poisson model's Z and TF.IDF weight for the three subsets showed that the correlation was relatively high for two test subsets with short texts, i.e., the Science and Technology subset and the Newspaper subset.

  • PDF

Content Analysis of the Articles of the Overseas Local Newspapers on the Culture Contents of Korea, China, and Japan -Focusing on Malaysia, Singapore, Mongolia, Uzbekistan, and Spain- (해외 현지신문의 한·중·일 문화콘텐츠 관련 기사의 내용분석 연구 -말레이시아, 싱가폴, 몽골, 우즈베키스탄, 스페인을 중심으로-)

  • Ahn, Cheunsoon;Narantuya, Lkhagva
    • Journal of the Korean Society of Clothing and Textiles
    • /
    • v.40 no.6
    • /
    • pp.1100-1115
    • /
    • 2016
  • This research investigated the relative influence of culture contents from Korea, China, and Japan published in the internet version of local newspapers for Malaysia, Mongolia, Uzbekistan, and Spain (from January 2010 to December 2014) and from Singapore (January 2012 to December 2014) using content analysis focused on the frequency distribution of newspaper content. 'Food' showed the highest appearance frequency of the 11 culture contents investigated in the study. Among the articles related to Korea, 'Pop Music' showed the highest frequency for Malaysia, Uzbekistan, and Spain and 'Star' showed the highest frequency for Singapore and Mongolia. Among the Hallyu related contents, 'Pop Music' showed the highest frequency followed by 'Star', 'Movie', and 'Drama'. Articles related to Korea showed a significantly higher frequency than articles related to China and Japan in 'Pop Music' and 'Star' categories. Spain showed articles related to Korea only in the 'Pop Music' category.

The Semantic Network Analysis of a Social Perspective on Conservation Discussions of 'Apartment Trace Remaining' - Focused on Newspaper Articles in Jamsil Jugong Apartment and Gaepo Jugong Apartment cases - ('아파트 흔적남기기'의 보존논의에 관한 사회적 관점의 의미네트워크 분석 - 잠실주공아파트와 개포주공아파트 사례의 신문기사를 중심으로 -)

  • Ahn, Jae-Cheol
    • Journal of the Regional Association of Architectural Institute of Korea
    • /
    • v.21 no.5
    • /
    • pp.109-116
    • /
    • 2019
  • The Seoul city recommended that old apartments be preserved, and as part of that, it decided to preserve some of the buildings for Jamsil Jugong, which was built in 1977, and Gaepo Jugong, which was constructed in 1981. The purpose of this study was to compare and review newspaper articles with two perspectives positive and negative about how the social perception of 'apartment trace remaining' was being constructed. By looking at the meaning of keywords delivered by newspaper articles and the interaction structure between keywords through the analysis of semantic networks, we analyzed how the media is pursuing an issue on the topic of preservation of architectural cultural heritage. The analysis results confirmed that there was a clear difference between positive and negative newspaper. Positive articles dealt with utilization from the point of view of keywords linked to preservation, and negative articles showed that keywords related to the property and backlash of residents linked to the policy of the Seoul Metropolitan Government were linked, leading to high negative public opinion.

A Study on the News Frame Analysis of Real Estate Policy (정부의 부동산 정책에 대한 언론의 보도 프레임 분석)

  • Kim, Sung-Yong;Oh, Sae-Joon
    • The Journal of the Korea Contents Association
    • /
    • v.16 no.7
    • /
    • pp.221-230
    • /
    • 2016
  • The public mostly get the information regarding real estate policy not from the press release of the government but from news articles. This type of information, though, might be delivered in a different frame depending on inclination of media or press. The media runs the articles within its own frame, so that it often conveys either expectation or concern depending on its inclination. This study analyzed the articles regarding 'Agreement to revise three major real estate regulations to perk up property market' and examined how the real estate policy imprinted in them depending on the disposition of the press. The results showed that the conservative press ran articles within a positive frame expressing favorable expectation. On the other hand, progressive press mostly kept neutral or unfavorable tone on the same regulations within the negative frame. Therefore, it was confirmed that there exist different frames within articles depending on their disposition.

Analysis of trade newspapers related to dental hygienists as healthcare professionals using language analysis technique: using R program (언어분석기법을 활용한 치과위생사의 의료인화 관련 신문기사 분석: R 프로그램 이용)

  • Kim, Song-Yi;Yoon, Ga-Rim;Kang, Dong-Hyun;Kim, Su-Jin;Lee, Si-Eun;Jang, Soo-Bin;Hong, Seong-Min;Hwang, Ji-Hoon;Kim, Nam-Hee
    • Journal of Korean society of Dental Hygiene
    • /
    • v.17 no.5
    • /
    • pp.921-930
    • /
    • 2017
  • Objectives: The purposes of this study were to analyze the trade newspapers related to 'recognition of the dental hygienist as the healthcare professional' using R program and to identify opinions of groups concerned with dental hygienists. Methods: This study was designed with contents analysis and cross-sectional. The subjects of the study were the articles for the last three years in medical and dental newspapers about the recognition of the dental hygienist as the healthcare professional. The collected articles were categorized and classified for each group's opinions about the issue. The key words were extracted according to the priorities of the opinions of agreement and disagreement. They were visualized after frequency analysis using R, a big data analysis program. Results: A total of 237 newspaper articles were extracted among 270 ones containing opinions. 245 were positive opinions and 25 were negatives. The main key words of the agreement were 'Amendment of Medical Law', 'Medical Practice', and 'Legal Guarantee of the Practice'. Advocates addressed that the issues should be resolved with the amendment of the law, as dental hygienists are not guaranteed to work based on the current law although they are actually doing the medical practices. Main key words of disagreement were 'Legal Guarantee of the Practice', 'Revision of Medical Technician Law', and 'Review of Job Type'. They described that the problem can be resolved by revising medical technicians act, and it needs to consider as job types of all healthcare professional. Conclusions: In the group who showed the positive opinions, it is possible to utilize measures such as promoting the cooperation of dental hygienists and developing public consensus through publicity.

A Study of Family Values on Newspaper Articles in May as 'Family Month' ('가정의 달' 신문 기사에 나타난 가족가치관 연구)

  • Kim, Minjee;Jun, Mikyung
    • Journal of Families and Better Life
    • /
    • v.34 no.2
    • /
    • pp.29-50
    • /
    • 2016
  • This study aims to find out tendencies of transition of family values in newspapers which were published in May. The study was conducted on content analysis of Chosun and Donga daily newspapers in odd dates of May from 1970 to 2014. Based on preceding research, family values were classified into sub areas such as 'Value of Family,' 'Value of Marriage,' 'Value of Children,' 'Value of Filial Piety' and 'Value of Sex Role.' The collected articles were classified into five sub areas. This study collected 288 articles considering overlap count. According to the study, the newspapers seem to be interested in 'Value of Family' and 'Value of Children', but not 'Value of Marriage'. And academic, social, political efforts to improve family life or raise a necessity to change family values can evoke mass media's interest about family values. Meanwhile, some newspaper articles appear to support an opinion that 'The Healthy Families Act' postulates a claim like 'the traditional family is a normal family'. It seems that newspapers misunderstood about 'The Healthy Families Act.' So we should judge what is more right between two opinions because mass media can reconstruct reality. The tendency of transition of family values is actually slight or the tendency of family values in newspapers cannot show actual family values. Moreover, we have to reconsider that highlighting just 'paternity' can make men overlook other roles in the household like caring for children or cleaning.

Categorization of Korean News Articles Based on Convolutional Neural Network Using Doc2Vec and Word2Vec (Doc2Vec과 Word2Vec을 활용한 Convolutional Neural Network 기반 한국어 신문 기사 분류)

  • Kim, Dowoo;Koo, Myoung-Wan
    • Journal of KIISE
    • /
    • v.44 no.7
    • /
    • pp.742-747
    • /
    • 2017
  • In this paper, we propose a novel approach to improve the performance of the Convolutional Neural Network(CNN) word embedding model on top of word2vec with the result of performing like doc2vec in conducting a document classification task. The Word Piece Model(WPM) is empirically proven to outperform other tokenization methods such as the phrase unit, a part-of-speech tagger with substantial experimental evidence (classification rate: 79.5%). Further, we conducted an experiment to classify ten categories of news articles written in Korean by feeding words and document vectors generated by an application of WPM to the baseline and the proposed model. From the results of the experiment, we report the model we proposed showed a higher classification rate (89.88%) than its counterpart model (86.89%), achieving a 22.80% improvement. Throughout this research, it is demonstrated that applying doc2vec in the document classification task yields more effective results because doc2vec generates similar document vector representation for documents belonging to the same category.