• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.767-770
• /
• 2018

인공지능의 발달로 사람이 사용하는 자연어 형태의 문장을 통해 정보를 주고받는 질의응답 시스템이 주목받고 있다. 이러한 질의응답 시스템은 자연어로 구성된 사용자의 질의문에서 의도를 정확하게 파악해야 한다. 단순히 질의어의 키워드에 의존한 검색은 단어의 중의성을 고려하지 않아 질의문의 의도를 정확히 파악하는 데 문제가 있다. 이런 문제점을 해결하기 위해 질의문의 의미와 맥락에 따른 연관성을 이용하여 유의어를 확장하는 방법이 연구되고 있다. 본 논문에서는 워드 임베딩을 통해 생성된 단어 유사도를 이용하여 질의문에서 추출된 키워드를 확장하는 방법을 제안한다.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.30 no.2
• /
• pp.167-187
• /
• 2019

Information behavior (IB) research in LIS and Health Information Seeking Behavior (HISB) in Health Medicine are two subject areas of research that have matured in the past few decades. This research aimed to compare these two research areas using a bibliometric approach. To conduct this study two distinct datasets were created using the Scopus database: a) bibliographic records of IB in the LIS domain, and b) bibliographic records of the HISB domain. The bibliometric analysis was performed according to the following criteria: published papers, citations, journal articles, author keywords, unique words in the title, words preceding "information" in the title, words preceding "study" in the title, and author keywords along with index keywords. As a result, the major differences in the two IB research areas were evident in terms of definitions, main focus, and general demographic groups. These varying types of differences suggest that researchers of the two areas should have flexibility when examining issues related to IB by considering the context and the unique distinction between the two fields.

• Journal of Information Management
• /
• v.23 no.1
• /
• pp.39-62
• /
• 1992

In this paper about 60 auxiliary words and 320 stopwords are selected from analysis of sample data, four types of stop word are classified left, right and - auxiliary word truncation & normal. And a keyword extraction system is suggested which undertakes efficient truncation of auxiliary word from words, conversion of Chinese word to Korean and exclusion of stopword. The selected keyeords in this system show 92.2% of accordance ratio compared with manually selected keywords by expert. And then compound words consist of $4{\sim}6$ character generate twice of additional new words and 58.8% words of those are useful as keyword.

• Journal of the Korean Society for information Management
• /
• v.39 no.1
• /
• pp.309-330
• /
• 2022

Intellectual structure analysis, which quantitatively identifies the structure, characteristics, and sub-domains of fields, has rapidly increased in recent years. Analysis techniques traditionally used to conduct intellectual structure analysis research include bibliographic coupling analysis, co-citation analysis, co-occurrence analysis, and author bibliographic coupling analysis. This study proposes a novel intellectual structure analysis method, Keyword Bibliographic Coupling Analysis (KBCA). The Keyword Bibliographic Coupling Analysis (KBCA) is a variation of the author bibliographic coupling analysis, which targets keywords instead of authors. It calculates the number of references shared by two keywords to the degree of coupling between the two keywords. A set of 1,366 articles in the field of 'Open Data' searched in the Web of Science were collected using the proposed KBCA technique. A total of 63 keywords that appeared more than 7 times, extracted from 1,366 article sets, were selected as core keywords in the open data field. The intellectual structure presented by the KBCA technique with 63 key keywords identified the main areas of open government and open science and 10 sub-areas. On the other hand, the intellectual structure network of co-occurrence word analysis was found to be insufficient in the overall structure and detailed domain structure. This result can be considered because the KBCA sufficiently measures the relationship between keywords using the degree of bibliographic coupling.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.180-185
• /
• 2015

As the number of document resources is continuously increasing, automatically extracting keyphrases from a document becomes one of the main issues in recent days. However, most previous works have tried to extract keyphrases from words in documents, so they overlooked latent keyphrases which did not appear in documents. Although latent keyphrases do not appear in documents, they can undertake an important role in text summarization and information retrieval because they implicate meaningful concepts or contents of documents. Also, they cover more than one fourth of the entire keyphrases in the real-world datasets and they can be utilized in short articles such as SNS which rarely have explicit keyphrases. In this paper, we propose a new approach that selects candidate keyphrases from the keyphrases of neighbor documents which are similar to the given document and evaluates the importance of the candidates with the individual words in the candidates. Experiment result shows that latent keyphrases can be extracted at a reasonable level.

• Journal of the Korean Society for information Management
• /
• v.35 no.2
• /
• pp.89-114
• /
• 2018

Research on changes in research trends in academic disciplines is a method that enables observation of not only the detailed research subject and structure of the field but also the state of change in the flow of time. Therefore, in this study, in order to observe the changes of research trend in library and information science field in Korea, co-word analysis was conducted with Korean author keywords from three types of journals which were listed in the Korea Citation Index(KCI) and have top citation impact factor were selected. For the time series analysis, the 15-year research period was accumulated in 5-years units, and divided into 2003~2007, 2003~2012, and 2003~2017. The keywords which limited to the frequency of appearance 10 or more, respectively, were analyzed and visualized. As a result of the analysis, during the period from 2003 to 2007, the intellectual structure composed with 25 keywords and 8 areas was confirmed, and during the period from 2003 to 2012, the structure composed by 3 areas 17 sub-areas with 76 keywords was confirmed. Also, the intellectual structure during the period from 2003 to 2017 was crowded into 6 areas 32 consisting of a total of 132 keywords. As a result of comprehensive period analysis, in the field of library and information science in Korea, over the past 15 years, new keywords have been added for each period, and detailed topics have also been subdivided and gradually segmented and expanded.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.583-586
• /
• 2023

대량 문자서비스를 통한 스팸 문자가 계속 증가하면서 이로 인해 도박, 불법대출 등의 광고성 스팸 문자에 의한 피해가 지속되고 있다. 이러한 문제점을 해결하기 위해 다양한 방법들이 연구되어 왔지만 기존의 방법들은 주로 사전 정의된 키워드나 자주 나오는 단어의 출현 빈도수를 기반으로 스팸 문자를 검출한다. 이는 광고성 문자들이 시스템에서 자동으로 필터링 되는 것을 회피하기 위해 비정상 문자를 조합하여 스팸 문자의 주요 키워드를 의도적으로 변형해 표현하는 경우에는 탐지가 어렵다는 한계가 있다. 따라서, 본 논문에서는 이러한 문제점을 해결하기 위해 딥러닝 기반 객체 탐지 및 OCR 기술을 활용하여 스팸 문자에 사용된 변형된 문자열을 정상 문자열로 복원하고, 변환된 정상 문자열을 문장 수준 이해를 기반으로 하는 자연어 처리 모델을 이용해 스팸 문자 콘텐츠를 분류하는 방법을 제안한다. 그리고 기존 스팸 필터링 시스템에 가장 많이 사용되는 키워드 기반 필터링, 나이브 베이즈를 적용한 방식과의 비교를 통해 성능 향상이 이루어짐을 확인하였다.

• Journal of the Korean Society for Library and Information Science
• /
• v.56 no.4
• /
• pp.431-453
• /
• 2022

Hate is a collective expression of exclusivity toward others and it is fostered and reproduced through false public perception. This study aims to explore the objects and issues of hate discussed in our society using text mining techniques. To this end, we collected 17,867 news data published from 1990 to 2020 and constructed a co-word network and cluster analysis. In order to derive an explicit co-word network highly related to hate, we carried out sentence split and extracted a total of 52,520 sentences containing the words 'hate', 'prejudice' and 'discrimination' in the preprocessing phase. As a result of analyzing the frequency of words in the collected news data, the subjects that appeared most frequently in relation to hate in our society were women, race, and sexual minorities, and the related issues were related laws and crimes. As a result of cluster analysis based on the co-word network, we found a total of six hate-related clusters. The largest cluster was 'genderphobic', accounting for 41.4% of the total, followed by 'sexual minority hatred' at 28.7%, 'racial hatred' at 15.1%, 'selective hatred' at 8.5%, 'political hatred' accounted for 5.7% and 'environmental hatred' accounted for 0.3%. In the discussion, we comprehensively extracted all specific hate target names from the collected news data, which were not specifically revealed as a result of the cluster analysis.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.619-623
• /
• 2020

한국어는 교착어로 1개 이상의 형태소가 단어를 이루고 있기 때문에 텍스트 분석 시 형태소를 분리하는 작업이 필요하다. 자연어를 처리하는 대부분의 알고리즘은 영미권에서 만들어졌고 영어는 굴절어로 특정 경우를 제외하고 일반적으로 하나의 형태소가 단어를 구성하는 구조이다. 그리고 영문은 주로 띄어쓰기 위주로 토큰화가 진행되기 때문에 텍스트 분석이 한국어에 비해 복잡함이 떨어지는 편이다. 이러한 이유들로 인해 한국어 텍스트 분석은 영문 텍스트 분석에 비해 한계점이 있다고 알려져 있다. 한국어 텍스트 분석의 성능 향상을 위해 본 논문에서는 번역 전처리 기법을 제안한다. 번역 전처리 기법이란 원본인 한국어 텍스트를 영문으로 번역하고 전처리를 거친 뒤 분석된 결과를 재번역하는 것이다. 본 논문에서는 한국어 뉴스 기사 데이터와 번역 전처리 기법이 적용된 영문 뉴스 텍스트 데이터를 사용했다. 그리고 주제어 역할을 하는 키워드를 단어 간의 유사도를 계산하는 알고리즘인 Word2Vec(Word to Vector)을 통해 유사 단어를 추출했다. 이렇게 도출된 유사 단어를 텍스트 분석 전문가 대상으로 성능 비교 투표를 진행했을 때, 한국어 뉴스보다 번역 전처리 기법이 적용된 영문 뉴스가 약 3배의 득표 차이로 의미있는 결과를 도출했다.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.1
• /
• pp.15-20
• /
• 2017

The purpose of this study is to present the intellectual structure of Assistive Technology Journal using co-word analysis of keywords. The articles of Assistive Technology Journal were collected from Web of Science citation database. 255 articles during the period from 2003 to 2015 were selected for the analysis. And 1,359 author keywords were extracted from the articles. In order to analyze the intellectual structure of Assistive Technology Journal, clustering analysis was conducted and 5 clusters were determined. Next, 5 clusters are presented in the map of multidimensional scaling. The results of this study are expected to assist in exploring the future directions of the researches on assistive technology.