• Proceedings of the Korean Information Science Society Conference
• /
• 2006.10b
• /
• pp.143-147
• /
• 2006

오늘날 웹의 비약적인 성장으로 텍스트, 이미지, 비디오, 그리고 사운드 등의 다양한 데이터 형식의 많은 정보가 축적되었으며 날마다 늘어나고 있다. 이들 정보의 효율적 검색을 위해 많은 연구가 이루어졌으며, 특히 텍스트 문서의 효율적인 검색을 위해 확률을 이용한 방법, 통계적인 기법을 이용한 방법, 벡터 유사도를 이용한 방법, 베이지안 자동문서 분류 방법 등이 제안되었다. 그러나 이러한 기존의 방법들은 문서의 특징을 정확하게 반영할 수 없고, 의미적 검색이 이루어지지 않는 단점을 가지고 있다. 이에 본 논문은 문서를 미리 분류하는 기존의 방법을 개선하기 위해, 사용자가 원하는 문서와 비슷한 문서를 의미적으로 찾아내기 위한 방법을 제안한다. 본 방법론은 문서의 내용을 의미적인 계층으로 표현하고 중요 도메인에 가중치를 두어 각 문서들의 계층들의 도메인 비중과 도메인 내의 개념 일치도를 이용하여 문서들 간에 유사도를 구한다.

• Annual Conference on Human and Language Technology
• /
• 2020.10a
• /
• pp.595-597
• /
• 2020

빅데이터 시대에서 대용량 문서의 의미를 자동으로 파악하기 위해서는 문서 내에서 주제 및 내용을 포괄하는 핵심 단어가 키워드 단위로 추출되어야 한다. 문서에서 키워드가 될 수 있는 단위는 복합명사를 포함한 단어가 될 수도, 그 이상의 묶음이 될 수도 있다. 한국어는 언어적 특성상 구묶음 개념이 적용되는 데, 이를 통해 주요 키워드가 될 수 있는 말덩이 추출이 가능하다. 따라서 본 연구에서는 문서에서 단어뿐만 아니라 다양한 단위의 키워드 묶음을 태깅하는 가이드라인 정의를 비롯해 태깅도구를 활용한 코퍼스 구축 방법론을 고도화하고, 그 방법론을 실제로 뉴스 도메인에 적용하여 주석 말뭉치를 구축함으로써 검증하였다. 본 연구의 결과물은 텍스트 문서의 내용을 파악하고 분석이 필요한 모든 텍스트마이닝 관련 기술의 기초 작업으로 활용 가능하다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.379-383
• /
• 2021

감정 분석은 텍스트 데이터에서 인간이 느끼는 감정을 다양한 감정 유형으로 분류하는 것이다. 그러나 많은 연구에서 감정 분석은 긍정과 부정, 또는 중립의 극성을 분류하는 감성 분석의 개념과 혼용되고 있다. 본 연구에서는 텍스트에서 느껴지는 감정들을 다양한 감정 유형으로 분류한 감정 말뭉치를 구축하였는데, 감정 말뭉치를 구축하기 위해 심리학 모델을 기반으로 분류한 감정 어휘 사전을 사용하였다. 9가지 감정 유형으로 분류된 한국어 감정 어휘 사전을 바탕으로 한국어 영화 리뷰 말뭉치에 9가지 감정 유형의 감정을 태깅하여 감정 분석 말뭉치를 구축하고, KcBert에 학습시켰다. 긍정과 부정으로 분류된 데이터로 사전 학습된 KcBert에 9개의 유형으로 분류된 데이터를 학습시켜 기존 모델과 성능 비교를 한 결과, KcBert는 다중 분류 모델에서도 우수한 성능을 보였다.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.13-31
• /
• 2016

Despite expectations of short- or long-term positive effects of corporate social responsibility (CSR) on firm performance, the results of existing research into this relationship are inconsistent partly due to lack of clarity about subordinate CSR concepts. In this study, keywords related to CSR concepts are extracted from atypical sources, such as newspapers, using text mining techniques to examine the relationship between CSR and firm performance. The analysis is based on data from the New York Times, a major news publication, and Google Scholar. We used text analytics to process unstructured data collected from open online documents to explore the effects of CSR on short- and long-term firm performance. The results suggest that the CSR index computed using the proposed text - online media - analytics predicts long-term performance very well compared to short-term performance in the absence of any internal firm reports or CSR institute reports. Our study demonstrates the text analytics are useful for evaluating CSR performance with respect to convenience and cost effectiveness.

• Journal of Broadcast Engineering
• /
• v.24 no.1
• /
• pp.48-57
• /
• 2019

The purpose of this study is to understand the intention of the inquirer from the single text type question in Goal-oriented dialogue. Goal-Oriented Dialogue system means a dialogue system that satisfies the user's specific needs via text or voice. The intention analysis process is a step of analysing the user's intention of inquiry prior to the answer generation, and has a great influence on the performance of the entire Goal-Oriented Dialogue system. The proposed model was used for a daily chemical products domain and Korean text data related to the domain was used. The analysis is divided into a speech-act which means independent on a specific field concept-sequence and which means depend on a specific field. We propose a classification method using the word embedding model and the CNN as a method for analyzing speech-act and concept-sequence. The semantic information of the word is abstracted through the word embedding model, and concept-sequence and speech-act classification are performed through the CNN based on the semantic information of the abstract word.

• Journal of The Korean Association For Science Education
• /
• v.27 no.5
• /
• pp.367-378
• /
• 2007

The purpose of this study is to investigate the features of science language in Earth science textbooks and Earth science research articles. We examined two Earth science textbooks and two Earth science articles using the taxonomy of scientific words, the text structure analysis of explanations, the analysis of conjunctive relations and reasoning, and the function of conjunction. The results showed that school science language revealed in Earth science textbooks had high proportion of naming words and the text structures in which definition/exemplification structure and description structure were dominant. Also, internal relations that showed additional arrangement rather than logical inference, were predominant in Earth science textbooks. However, scientists' science language revealed in the Earth science articles had more proportion of process words and concept words than the Earth science textbooks and the schematic structure of explanation texts, such as orientation - implication sequence - conclusion. In addition, the text structures in each sentences of implication -sequence showed cause/effect or problem-solving after description structures. Also each sentences expressed causal or abductive reasoning through the internal relations using verbs or adverbial inflection. It is necessary that we bridge the gap between the two languages for students' authentic use of science language. For the bridging, we propose "interlanguage", which mediates between school science language and scientists' language.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.15 no.6
• /
• pp.10-23
• /
• 2016

With requiring circumspections using big data, this study attempts to develop and apply the search method for audit issues relating to the ITS policy or program. For the foregoing, the auditing process of the board of audit and inspection was converged with the theoretical frame of boundary analysis proposed by William Dunn as an analysis tool for audit issues. Moreover, we apply the text mining technique in order to computerize the analysis tool, which is similar to the boundary analysis in the concept of approaching meta-problems. For the text mining analysis, specific model we applied the antisymmetry-symmetry compound lexeme-based LDA model based on the Latent Dirichlet Allocation(LDA) methodologies proposed by David Blei. The several prime issues were founded through a case analysis as follows: lack of collection of traffic information by the urban traffic information system, which is operated by the National Police Agency, the overlapping problems between the Ministry of Land, Infrastructure and Transport and the Advanced Traffic Management System and fabrication of the mileage on digital tachograph.

• Journal of Cadastre & Land InformatiX
• /
• v.49 no.1
• /
• pp.113-121
• /
• 2019

The fourth industrial revolution technology focused on the fusion of infrastructure and various advanced technologies related city. Therefore, technical cooperation in various fields of research is essential. In order to activating the fourth industrial revolution technologies, it is necessary to research the state of technology in various fields. Consequently, this paper aims to analysis of domestic and foreign research trends on technology to the fourth industrial revolution using SNA and text mining for web site. We collected text, date data of research paper and report in web site for five years, that is, from January 1st in 2014 to December 31st in 2018. Next, we have deduced the major keywords in public data through analyzing the morphemes. Then we have analyzed the core and related keyword lists through an SNA. In Korea, the focus is on R&D and legal/institutional solution in relation to the fourth industrial revolution technology. On the other hand, in the case of foreign, there was focus on practical technologies for urban services in detail aspects.

• The Southeast Asian review
• /
• v.28 no.3
• /
• pp.75-110
• /
• 2018

This study is to figure out the Filipino cultural identity by analyzing the image of the Philippine comfort woman statue, which was created as a representation of memories of the Filipino comfort women during the World War II. As a new approach to the field of area study, this study introduced the concept of 'intertextuality', which is a method of understanding texts in the field of literature. Since the comfort woman statue represents the grieved memories of the comfort women during the international war time, the analysis of the image was focused on 'femininity' and 'nationalism'. As for comparison, the Korean comfort woman statue, the Statue of Peace, was taken into the analysis. Upon analyzing, it can be seen that Filipino perception of femininity emphasizes 'beauty' rather than 'purity' that expressed in the Statue of Peace. And the Philippine nationalism expressed through the comfort woman statue can find 'elitist and inclusive' characteristics, unlike the 'popular and resisting' characteristics of Korean.

• Information Systems Review
• /
• v.18 no.1
• /
• pp.141-155
• /
• 2016

This study identified terminologies related to the proximity and frequency of disaster by social network analysis (SNA) and text mining, and then expressed the outcome into a mind map. The termdocument matrix of text mining was utilized for the terminology proximity analysis, and the SNA closeness centrality was calculated to organically express the relationship of the terminologies through a mind map. By analyzing terminology proximity and selecting disaster response-related terminologies, this study identified the closest field among all the disaster response fields to disaster response and the core terms in each disaster response field. This disaster response terminology analysis could be utilized in future core term-based terminology standardization, disaster-related knowledge accumulation and research, and application of various response scenario compositions, among others.