• Proceedings of the Korean Information Science Society Conference
• /
• 2007.06d
• /
• pp.356-360
• /
• 2007

인터넷이 폭 넓게 보급되어 개인의 의견을 개진할 기회가 확대됨에 따라 정치, 경제 등의 사안이나 제품 기업의 이미지, 공인에 대한 긍정.부정의 글을 개진할 수 있게 되었다. 이러한 현상에 따라 기업, 제품, 혹은 공공의 분야에서 일반 개인들이 어떻게 생각하는가에 대한 분석 및 자료수집의 필요성이 높아지고 있다. 감성용어 문서분류시스템은 문서의 내용 중 감성기반의 용어들에 기반하여 이에 대한 패턴을 정의하고 이에 대응하는 범주에 문서를 자동으로 할당하는 작업으로써 효율적인 정보 관리 및 검색을 가능하게 한다. 하지만 자동문서 분류를 하기 위해서는 방대한 양의 데이터를 수집 보관하기 위한 분산 환경이 반드시 필요하다. 본 논문에서는 감성기반 문서분류 시스템을 위한 감성용어 추출 및 긍정, 부정의 패턴을 검색해 자동 문서분류를 위해 RTI(Run Time Infrastructure)를 통한 분산 시스템 환경으로 구성하였다.

• Proceedings of the Korean Society for Information Management Conference
• /
• 2014.08a
• /
• pp.119-122
• /
• 2014

본 연구는 교육학 분야에서 국내 학술 논문 저자키워드 출현 순서에 의미가 있는지 알아보기 위하여 저자키워드 출현 순서별로 빈도를 조사하고 동 저자 키워드가 제목에 출현하는지를 살펴본 후, 학술논문 저자키워드 출현 순서에 따른 빈도가 저자키워드의 논문 제목 출현 빈도에 미치는 영향에 대해 연구하고자 한다. 연구의 배경은 구조적 학술용어사전의 구축과 관련해서 효율적인 용어 선정이나 용어 분류 방법을 찾는 것이다. 연구의 목적을 위해 교육학 분야 저자키워드의 출현 빈도수가 1인 것을 제외하고 고빈도 순으로 400개 용어를 추출하였다. 저자키워드의 몇 번째 출현 순서가 저자키워드의 제목 출현에 가장 큰 영향을 미치는지 알아본 결과, 저자키워드의 첫 번째 출현이 아닌 두 번째 출현이 가장 큰 영향을 미친다는 것을 알 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.12 no.10
• /
• pp.1-10
• /
• 2012

Many statistical methods have been adapted for terminology recognition to improve its accuracy. However, since previous studies have been carried out in a single core or a single machine, they have difficulties in real-time analysing explosively increasing documents. In this study, the task where bottlenecks occur in the process of terminology recognition is classified into linguistic processing in the process of 'candidate terminology extraction' and collection of statistical information in the process of 'terminology weight assignment'. A terminology recognition system is implemented and experimented to address each task by means of the distributed parallel processing-based MapReduce. The experiments were performed in two ways; the first experiment result revealed that distributed parallel processing by means of 12 nodes improves processing speed by 11.27 times as compared to the case of using a single machine and the second experiment was carried out on 1) default environment, 2) multiple reducers, 3) combiner, and 4) the combination of 2)and 3), and the use of 3) showed the best performance. Our terminology recognition system contributes to speed up knowledge extraction of large scale science and technology documents.

• Management & Information Systems Review
• /
• v.37 no.4
• /
• pp.41-62
• /
• 2018

As the volume of unstructured data increases through various social media, Internet news articles, and blogs, the importance of text analysis and the studies are increasing. Since text analysis is mostly performed on a specific domain or topic, the importance of constructing and applying a domain-specific dictionary has been increased. The quality of dictionary has a direct impact on the results of the unstructured data analysis and it is much more important since it present a perspective of analysis. In the literature, most studies on text analysis has emphasized the importance of dictionaries to acquire clean and high quality results. However, unfortunately, a rigorous verification of the effects of dictionaries has not been studied, even if it is already known as the most essential factor of text analysis. In this paper, we generate three dictionaries in various ways from 39,800 news articles and analyze and verify the effect each dictionary on the accuracy of document classification by defining the concept of Intrinsic Rate. 1) A batch construction method which is building a dictionary based on the frequency of terms in the entire documents 2) A method of extracting the terms by category and integrating the terms 3) A method of extracting the features according to each category and integrating them. We compared accuracy of three artificial neural network-based document classifiers to evaluate the quality of dictionaries. As a result of the experiment, the accuracy tend to increase when the "Intrinsic Rate" is high and we found the possibility to improve accuracy of document classification by increasing the intrinsic rate of the dictionary.

• Journal of Digital Convergence
• /
• v.17 no.1
• /
• pp.449-456
• /
• 2019

This study attempted to improve the quality of hairstyling-related studies and provide basic data for future studies on hairstyling terms through analysis of cosmetology-related loan words used in hairstyling theses among recent cosmetology papers. For data collection to derive valid conclusions, the signatures of a total of 1,980 academic papers collected after typing in the keyword 'Hair' at the Research Information Sharing Service (http://www.riss.kr) were analyzed. The results show that researchers in hairstyling seem not to pay close attention to the correct use of foreign loan words. Therefore, the study results would be very helpful to the development of future cosmetology studies. The correct notation and use of foreign loanwords should be further encouraged.

• Journal of Science Education
• /
• v.36 no.2
• /
• pp.329-340
• /
• 2012

The purpose of this study is to analyze the terms which were described in panels for astronomic article on exhibition at the Gwacheon National Science Museum, and to clarify that the terms were appropriate and easily understandable or not. In research, totally, 965 terms were collected in 52 panels(14 panels in planetarium, 17 panels in national history part, and 21 panels in traditional science part). All terms were categorized to 4types, as 1.Standard/Scientific terms, 2.Non-Standard/Scientific terms, 3.Standard/Non-Scientific terms, 4. Non-Standanrd/Non-Scientific casual words, based on 'Dictionary of Standard Korean' and 'Terminology of Astronomy'. And questionnaires survey was done to 24 in-service teachers at elementary school, middle school, and high school to clarify that the level of the terms are appropriate to students. The results of this study show that accurate scientific terms were 68.5%, and many of students had difficulty in understanding those scientific terms in the panels because of unfamiliarity. Therefore, in order to make students get more interest and better understanding, it is proposed to minimize scientific terms and to substitute them to casual terms which were related with practical life.

• The Journal of the Korea Contents Association
• /
• v.11 no.8
• /
• pp.247-259
• /
• 2011

It is necessary to collect, manage and standardize defense and technology terminologies which are used by defense-related agencies in the field of national defense science and technology. The standardization of terminology dictionary can eliminate confusion about terminology and increase accessibility for the terminology by offline and online services. This study focuses on building national defense science and technology terminologies, publishing dictionary including them, and improving information analysis in defense area. as well as take advantage of offline and online services for easy accessibility for the terminology. Based on the results of this study, the terminology data will be used as follows; 1) Defence science and technology terminology databases and its publication. 2) Information analysis in military fields. 3) Multilingual information analysis translated terms in the thesauri. 4) Verification on the consistency of information processing. 5) Language resources for terminology extraction.

• Journal of the Korean earth science society
• /
• v.29 no.4
• /
• pp.363-371
• /
• 2008

The purposes of this study were to analyze the level of Earth science vocabularies in the 10th grade textbooks with the Science Word Analysis (SWA) program and to investigate the vocabularies selected by the 10th grade students as difficult ones. For this purpose, we extracted the Earth science vocabularies from eleven textbooks, and classified into scientific and non-scientific vocabularies with the SWA program based on the standard Korean language dictionary. In addition, we investigated the difficulty of each vocabulary by surveying five hundred sixty students with a questionnaire. Results showed that the frequency of the scientific vocabularies that were beyond the designated level was the largest among any other levels in all textbooks. Most of the vocabularies selected by students as difficult ones to understand were classified into out of the level. From these results, it were suggested that the students' cognitive level should be considered when developing science textbooks and difficult vocabularies should be replaced with easy ones without a change of meaning.

• Proceedings of the Korea Association of Information Systems Conference
• /
• 1997.10a
• /
• pp.83-88
• /
• 1997

시스템 성능을 개선하고 변화하는 환경에 적응하기 위해서는 기존 시스템을 실험, 분석함으로써 정확한 이해를 획득하고 나아가 재사용 자원으로 활용할 수 있는 소프트웨어 역공학이 필요하다. 또한 설계 문제의 추상화와 특정 영역의 일반적인 해결책에 대한 정보 표현 및 그 관계는 패턴 형식을 통해 효과적으로 나타낼 수 있다. 즉, 시스템의 설계 구조 를 추출하여 시스템 분석과 설계를 향상시키고 표준화 된 설계 용어 및 컴퍼넌트 관계 구조 를 통해 재사용을 용이하게 하는 설계 패턴 추출을 위한 역공학은 중요하다. 따라서 본 논 문에서는 기존 코드에서 설계 패턴 추출을 위한 역공학 적용의 타당성과 설계 패턴 자동 추 출을 위한 몇 개의 알고리즘을 살펴보고 간단히 적용시켜 본다.

• Journal of Practical Engineering Education
• /
• v.15 no.2
• /
• pp.321-330
• /
• 2023

In this paper, we propose a method of automatically creating an ontology by extracting various relationships between terms necessary for constructing an ontology of a specific domain. The extracted relationship is constructed as an ontology by encoding it into an axiomatic set in the structure of the ontology. To solve efficiently, we represent the search space of the set as an integer programming problem, and we reduce the matrix by using a simple reduction that eliminates rules that are not very helpful for optimization. In conclusion, this paper proposes a way to generalize patterns using given data, reduce search space while maintaining useful patterns, and automatically generate efficient ontology using extracted relationships by applying algorithms composed of structured ontology.