• 지능정보연구
• /
• 제20권2호
• /
• pp.123-136
• /
• 2014

최근 온라인 및 다양한 스마트 기기의 사용이 확산됨에 따라 온라인을 통한 쇼핑구매가 더욱 활성화 되었다. 때문에 인터넷 쇼핑몰들은 쇼핑에 관심이 있는 잠재 고객들에게 한 번이라도 더 자사의 링크를 노출시키기 위해 키워드에 비용을 지불할 용의가 있으며, 이러한 추세는 검색 광고 시장의 광고비를 증가시키는 원인을 제공하였다. 이 때 키워드의 가치는 대체로 검색어의 빈도수에 기반을 두어 산정된다. 하지만 포털 사이트에서 검색어로 자주 입력되는 모든 단어가 쇼핑과 관련이 있는 것은 아니며, 이들 키워드 중에는 빈도수는 높지만 쇼핑몰 관점에서는 별로 수익과 관련이 없는 키워드도 다수 존재한다. 그렇기 때문에 특정 키워드가 사용자들에게 많이 노출된다고 해서, 이를 통해 구매가 이루어질 것을 기대하여 해당 키워드에 많은 광고비를 지급하는 것은 매우 비효율적인 방식이다. 따라서 포털 사이트의 빈발 검색어 중 쇼핑몰 관점에서 중요한 키워드를 추출하는 작업이 별도로 요구되며, 이 과정을 빠르고 효과적으로 수행하기 위한 자동화 방법론에 대한 수요가 증가하고 있다. 본 연구에서는 이러한 수요에 부응하기 위해 포털 사이트에 입력된 키워드 중 쇼핑의도를 포함하고 있을 가능성이 높을 것으로 추정되는 키워드만을 자동으로 추출하는 방안을 제시하고, 구체적으로는 전체 검색어 중 검색결과 페이지에서 쇼핑과 관련 된 페이지로 이동한 검색어만을 추출하여 순위를 집계하고, 이 순위를 전체 검색 키워드의 순위와 비교하였다. 국내 최대의 검색 포털인 'N'사에서 이루어진 검색 약 390만 건에 대한 실험결과, 제안 방법론에 의해 추천된 쇼핑의도 포함 키워드가 단순 빈도수 기반의 키워드에 비해 정확도, 재현율, F-Score의 모든 측면에서 상대적으로 우수한 성능을 보이는 것으로 나타남을 확인할 수 있었다.

• 한국IT서비스학회지
• /
• 제18권4호
• /
• pp.135-149
• /
• 2019

Recently, there are many researches for extracting meaningful information from large amount of text data. Among various applications to extract information from text, topic modeling which express latent topics as a group of keywords is mainly used. Topic modeling presents several topic keywords by term/topic weight and the quality of those keywords are usually evaluated through coherence which implies the similarity of those keywords. However, the topic quality evaluation method based only on the similarity of keywords has its limitations because it is difficult to describe the content of a topic accurately enough with just a set of similar words. In this research, therefore, we propose topic keywords reorganizing method to improve the identifiability of topics. To reorganize topic keywords, each document first needs to be labeled with one representative topic which can be extracted from traditional topic modeling. After that, classification rules for classifying each document into a corresponding label are generated, and new topic keywords are extracted based on the classification rules. To evaluated the performance our method, we performed an experiment on 1,000 news articles. From the experiment, we confirmed that the keywords extracted from our proposed method have better identifiability than traditional topic keywords.

• 한국도서관정보학회지
• /
• 제48권1호
• /
• pp.207-225
• /
• 2017

본 연구의 목적은 키워드 특징 면에서 문헌정보 저널에서 나타나는 유사점과 차이점을 조사하여 다양한 문헌 정보학 연구 영역을 발견하는 데 있다. 이 연구를 수행하기 위해 2004 년부터 2016 년까지 네 개의 한국 저널의 키워드가 RISS 데이타베이스에서 수집 되었고(http://www.riss.co.kr) 그리고 여섯 개의 국제저널의 키워드가 SCOPUS 데이타베이스에서 수집 되었다(http://www.scopus.com). 키워드의 특징은 한국 및 국제저널에 관하여서 자주 사용 되었던 키워드와 자주 사용되었던 독특한 키워드를 검증하는 연구이었다. 독특한 키워드란 한 분야에서는 나타나지만 다른 분야에서는 나타나지 않는 키워드를 말한다. 이 연구의 결과는 다음과 같다. 가) 키워드 빈도 분석 결과는 한국의 문헌정보 학의 연구주제와 연구특색을 보여 주는 것으로 나타났다. 나) 일반적으로 한국 저널에서 사용 된 키워드는 도서관과 관련된 주제의 영역을 나타냈고, 국제 저널에 사용되는 키워드는 서지 측정법과 관련된 주제 영역을 나타냈다. 다) 빈번히 사용되었던 독특한 키워드에서도 이러한 전반적인 연구 테마를 명백히 나타냈다. 라) 어떤 키워드는 쓰이는 범위가 한 국가나 지역으로 한정되어 있는 것으로 나타냈다. 이 연구의 중요한 시사점은 가장 자주 사용되는 키워드와 가장 자주 사용되는 독특한 키워드는 둘 다 문헌정보 학의 주제 영역을 적절하게 반영하고 있는 것으로 보인다는 것이다.

• 한국초등과학교육학회지:초등과학교육
• /
• 제36권2호
• /
• pp.113-128
• /
• 2017

This study aims to investigate the research trend of elementary environmental education. Thus, author keywords were extracted from a total of 197 academic these related to elementary environmental education during two different periods when detailed goals were applied to the 2007 and 2009 revised curriculums respectively, and then this study analyzed the network of author keywords. The results of this study can be summarized as below. Firstly, as a result of analyzing the frequency of author keywords from academic theses related to elementary environmental education, this study discovered 369 author keywords from the period when detailed goals were applied to 2009 revised curriculum. Out of them, it was found that the keyword, 'climate change education', showed the highest frequency, followed by 'environmental literacy' and 'environmental perception', except such central keywords as 'environmental education' and 'elementary school student'. From the period when detailed goals were applied to the 2007 revised curriculum, a total of 394 author keywords were discovered, and the keyword, 'environmental literacy', showed the highest frequency, followed by 'environmental perception' and 'ESD (education for sustainable development)'. Secondly, as a result of analyzing the network of author keywords, this study found out that in the total number of network connections, average connection degree, density and clique, the period when detailed goals were applied to the 2007 revised curriculum was somewhat higher than the period when detailed goals were applied to the 2009 revised curriculum. As a result of analyzing the centrality of author keywords, this study found out that during both the periods, 'environmental perception' and 'environmental literacy' were high in degree centrality and betweenness centrality, except such central keywords as 'environmental education' and 'elementary school student'. As a result of analyzing the components of author keywords as sub-networks, this study discovered 9 components from the period when detailed goals were applied to the 2009 revised curriculum and 6 components from the period when detailed goals were applied to the 2007 revised curriculum. During both the periods, the largest component was composed of keywords high in degree centrality and betweenness centrality.

• 한국정보시스템학회지:정보시스템연구
• /
• 제28권4호
• /
• pp.271-291
• /
• 2019

Purpose The purpose of this study is to propose a methodology to derive positive keywords and negative keywords through deep learning to classify reviews into positive reviews and negative ones, and then refine the results of topic modeling using these keywords. Design/methodology/approach In this study, we extracted topic keywords by performing LDA-based topic modeling. At the same time, we performed attention-based deep learning to identify positive and negative keywords. Finally, we refined the topic keywords using these keywords as filters. Findings We collected and analyzed about 6,000 English reviews of Gyeongbokgung, a representative tourist attraction in Korea, from Tripadvisor, a representative travel site. Experimental results show that the proposed methodology properly identifies positive and negative keywords describing major topics.

• 대한간호학회지
• /
• 제35권7호
• /
• pp.1420-1425
• /
• 2005

Purpose: We try to disclose how much the keywords of the papers from the Journal of the Korean Academy of Nursing coincide with MeSH terminologies and to understand the major subjects of the recent nursing research in Korea from keywords. Methods: Keywords of journals were extracted and compared with MeSH terms. The frequency of the appearance of each keyword was sorted by a descending order. Results: Coincidence rate of 1,235 keywords with MeSH terms was $51.6\%$. Out of them, depression, elderly, stress, self efficacy, quality of life, exercise, middle-aged women, and women appeared most frequently in descending order. Conclusion: Coincidence rate of the keywords with MeSH terms was at an acceptable level, however to improve it, the education of submitters and editorial board members are required, as well as the copy editor, to take a role in checking keywords. To infer the subjects of the research from keywords might well represent the recent topics of research work.

• 한국정보시스템학회지:정보시스템연구
• /
• 제30권1호
• /
• pp.123-149
• /
• 2021

Purpose The purpose of this study is to define the anti-ESG activities of companies recognized by media by reflecting ESG recently attracted attention. This study extracts keywords for ESG controversies through association rule mining. Design/methodology/approach A research framework is designed to extract keywords for ESG controversies as follows: 1) From DeepSearch DB, we collect 23,837 articles on anti-ESG activities exposed to 130 media from 2013 to 2018 of 294 listed companies with ESG ratings 2) We set keywords related to environment, social, and governance, and delete or merge them with other keywords based on the support, confidence, and lift derived from association rule mining. 3) We illustrate the importance of keywords and the relevance between keywords through density, degree centrality, and closeness centrality on network analysis. Findings We identify a total of 26 keywords for ESG controversies. 'Gapjil' records the highest frequency, followed by 'corruption', 'bribery', and 'collusion'. Out of the 26 keywords, 16 are related to governance, 8 to social, and 2 to environment. The keywords ranked high are mostly related to the responsibility of shareholders within corporate governance. ESG controversies associated with social issues are often related to unfair trade. As a result of confidence analysis, the keywords related to social and governance are clustered and the probability of mutual occurrence between keywords is high within each group. In particular, in the case of "owner's arrest", it is caused by "bribery" and "misappropriation" with an 80% confidence level. The result of network analysis shows that 'corruption' is located in the center, which is the most likely to occur alone, and is highly related to 'breach of duty', 'embezzlement', and 'bribery'.

• 대한안전경영과학회지
• /
• 제25권1호
• /
• pp.1-6
• /
• 2023

This study tried to analyze the keywords of the papers published in the Korea Safety Management Science by using the social network analysis. In order to extract the keywords, information on journal articles published from 2018 to 2021 was extracted from the SCIENCE ON. Among the keywords extracted from a total of 129 papers, the keywords with similar meanings were standardized. The keywords used in the same paper were visualized by connecting them through a network. Four centrality indicators of the social network analysis were used to analyze the effect of the keyword. Safety, Safety management, Apartment, Fire hose, SMEs, Virtual reality, Machine learning, Waterproof time, R&D capability, and Job crafting were selected as the keywords analyzed with high influence in the four centrality indicators.

• 한국응급구조학회지
• /
• 제16권2호
• /
• pp.43-51
• /
• 2012

Purpose : We try to disclose how much the keywords of the papers from the Korean Journal of Emergency Medical Services with Medical Subject Headings(MeSH) terminologies and to understand the major subjects of the recent emergency medical technology research in Korea from keywords. Methods : We analyzed keywords from 524 articles of the Korean Journal of Emergency Medical Services that were published between 2005 and 2011. We investigated frequently used keywords and what percentages of keywords agree with MeSH terms using the MeSH browser. Results : There were on average 3.2 keywords per article. The most frequent key words were AED, Attitude, Cardiopulmonary Resuscitation, CPR, EMT, EMT students, External Defibrillator, Job satisfaction, Knowledge, 119 EMT in order. The number of terms in precise agreement with MeSH headings was 101(19.3%); 327 terms(62.4%) were not found in the MeSH browser and 96 terms(18.3%) partially matched MeSH terms. Conclusion : Many keywords used in the Korean Journal of Emergency Medical Services did not agree with MeSH terms. We conclude that contribution rules should be using MeSH terms and authors should be educated in the proper use of MeSH terms in their research and subsequent publication.

• 대한물리의학회지
• /
• 제7권3호
• /
• pp.367-377
• /
• 2012

Purpose : The purpose of this study was to investigate the coincidence between keywords of Journal of the Korean Society of Physical Medicine (JKSPM) and MeSH terms, a controlled vocabulary used in MEDLINE. Methods : A total of 838 keywords used in 252 papers of JKSPM from Vol.1, No.1, 2006 to Vol.7, No.1, 2012 were compared with MeSH terms. All of keywords are classified to three large categories; complete coincidence, incomplete coincidence, and complete incoincidence. Results : The keywords in complete coincidence category were 183(21.8%), the keywords in incomplete coincidence category were 378(45.1%), and the keywords in complete incoincidence category were 277(33%). The most used keyword in complete coincidence category was 'stroke' and in complete incoincidence category was 'balance'. The most used keyword matching entry terms in incomplete coincidence category was 'elderly'. Conclusion : The rate of complete coincidene of keywords with MeSH terms was not higher than the rates of incomplete coincidence and complete incoincidence. It is necessary to understand MeSH terms more accurately and specifically. The JKSPM should ask the authors to use MeSH terms as keyword when they submit the paper.