• Journal of Digital Convergence
• /
• v.18 no.9
• /
• pp.181-190
• /
• 2020

The purpose of this study is to analyze the trends of wearable keywords using text mining methodology. To this end, 11,952 newspaper articles were collected from 1992 to 2019, and frequency analysis and bi-gram analysis were applied. The frequency analysis showed that Samsung Electronics, LG Electronics, and Apple were extracted as the highest frequency words, and smart watches and smart bands continued to emerge as higher frequency in terms of devices. As a result of the analysis of the bi-gram, it was confirmed that the sequence of two adjacent words such as world-first and world-largest appeared continuously, and related new bi-gram words were derived whenever issues or events occurred. This trend of wearable keywords will be useful for understanding the wearable trend and future direction.

• 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.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06a
• /
• pp.225-228
• /
• 2011

본 논문은 비교 마이닝(comparison mining) 의 일환인 비교 요소 자동 추출에 관하여 연구한다. 비교 마이닝은 텍스트 마이닝의 한 분야로서 대용량의 텍스트를 대상으로 비교 관계롤 자동 분석하며, 비교 문장인지 아닌지를 식별하는 단계, 비교 타입을 분류하는 단계, 다양한 비교 요소들을 추출하는 단계, 추출된 요소를 분석 및 요약하는 단계 등을 거치게 된다. 본 연구에서는 특정 타입의 비교 문장이 주어졌을때, 그 문장에서 비교 요소를 자동으로 추출하는 단계의 과제를 수행하며, 우열 비교 타입 및 최상급 타입 문장들을 대상으로 비교 주체, 비교 대상, 비교 술어를 추출한다. 실험 과정으로는, 우선 비교 요소 후보들을 선정하고, 그 후 각 요소별로 확률을 계산하여 가장 높은 수치를 기록한 요소를 정답으로 채택하게 된다. 확률 계산은 지지 벡터 기계 (Support Vector Machine)를 이용한다. 인터넷 상의 다양한 도메인에서 추출된 비교 문장들을 대상으로 비교 요소 추출을 수출한 결과, 정확도 86.81 %의 우수한 성능을 산출 할 수 있었다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2018.07a
• /
• pp.59-62
• /
• 2018

XML을 대상으로 하는 연구가 최근 5~6년 사이에 꾸준한 증가를 보이며 이루어지고 있지만 대다수의 연구들은 XML을 구성하고 있는 엘리먼트 자체에 대한 통계적인 모델을 기반으로 이루어졌다. 이는 XML의 고유 속성인 트리 구조에서의 텍스트, 문장, 문장 구성 성분이 가지고 있는 의미(semantics)가 명시적으로 분석, 표현되어 사용되기 보다는 통계적인 방법으로만 데이터의 발생을 계산하여 사용자가 요구한 질의에 대한 결과, 즉 해당하는 정보 및 지식을 제공하는 형식이다. 지능형 지식서비스 제공을 위한 환경에 부합하기 위한 정보 추출은, 텍스트 및 문장의 구성 요소를 분석하여 문서의 내용을 단순한 단어 집합보다는 풍부한 의미를 내포하는 형식으로 표현함으로써 보다 정교한 지식과 정보의 추출이 수행될 수 있도록 하여야 한다. 본 연구는 범람하는 XML 데이터로부터 사용자 요구의 의미까지 파악하여 정확하고 다양한 지식을 추출할 수 있는 방법을 연구하고자 한다. 레코드 구조가 아닌 트리 구조 데이터로부터 의미 추출이 가능한 효율적인 마이닝 기법을 진일보시킴으로써 다양한 사용자 중심의 서비스 제공을 최종 목적으로 한다.

• Journal of the Korean Society for information Management
• /
• v.37 no.3
• /
• pp.253-274
• /
• 2020

In this study, text mining and main path analysis (MPA) were applied to understand the origins and development paths of research areas that make up the mainstream of Korean studies. To this end, a quantitative analysis was attempted based on digital texts rather than the traditional humanities research methodology, and the main paths of Korean studies were extracted by collecting documents related to Korean studies including citation information using a citation database, and establishing a direct citation network. As a result of the main path analysis, two main path clusters (Korean ancient agricultural culture (history, culture, archeology) and Korean acquisition of English (linguistics)) were found in the key-route search for the Humanities field of Korean studies. In the field of Korean Studies Humanities and Social Sciences, four main path clusters were discovered: (1) Korea regional/spatial development, (2) Korean economic development (Economic aid/Soft power), (3) Korean industry (Political economics), and (4) population of Korea (Sex selection) & North Korean economy (Poverty, South-South cooperation).

• Journal of Digital Convergence
• /
• v.18 no.3
• /
• pp.1-12
• /
• 2020

The purpose of this study is to explore the trend of blockchain technology through analysis of patents and news articles using text mining, and to suggest the blockchain policy agenda by grasping social interests. For this purpose, 327 blockchain-related patent abstracts in Korea and 5,941 full-text online news articles were collected and preprocessed. 12 patent topics and 19 news topics were extracted with latent dirichlet allocation topic modeling. Analysis of patents showed that topics related to authentication and transaction accounted were largely predominant. Analysis of news articles showed that social interests are mainly concerned with cryptocurrency. Policy agendas were then derived for blockchain development. This study demonstrates the efficient and objective use of an automated technique for the analysis of large text documents. Additionally, specific policy agendas are proposed in this study which can inform future policy-making processes.

• Journal of Digital Convergence
• /
• v.18 no.7
• /
• pp.93-99
• /
• 2020

Text mining is one of the big data analysis methods that extracts meaningful information from atypical large-scale text data. In this study, text mining was used to monitor citizens' opinions on the policies and systems being implemented. We collected 5,108 newspaper articles and 748 online cafe posts related to 'Gyeonggi Lacal Currency' and performed frequency analysis, TF-IDF analysis, association analysis, and word tree visualization analysis. As a result, many articles related to the purpose of introducing local currency, the benefits provided, and the method of use. However, the contents related to the actual use of local currency were written in the online cafe posts. In order to revitalize local currency, the news was involved in the promotion of local currency as an informant. Online cafe posts consisted of the opinions of citizens who are local currency users. SNS and text mining are expected to effectively activate various policies as well as local currency.

• Journal of Korea Port Economic Association
• /
• v.36 no.3
• /
• pp.39-54
• /
• 2020

In the presidential political system, the word of the president has great influence on the formation of national policy and the decision-making process. Policy priorities are determined according to the president's ideology and core values, and various policies are established and executed according to the priorities. Therefore, this paper analyzes the contents of the president's speech. Since the president's speech is a semantic datum, in order to analyze unstructured text, big data analysis is conducted through the methods of machine learning and deep learning. In this study, the president's speech at the "National Sea Day" commemoration was obtained 1996 onwards and analyzed using topic modeling. As a result of the analysis, all the presidents' speeches were delivered with a view of the ocean that was consistent with the direction of their administration. It was confirmed that the ocean-industry-resource topics, which are the intrinsic values of the ocean, were not damaged and consistently emphasized by all presidents.

• Annual Conference on Human and Language Technology
• /
• 2014.10a
• /
• pp.73-77
• /
• 2014

문장을 대상으로 특정 응용 분야에 필요한 요소를 자동으로 추출하는 정보 추출(information extraction) 과제는 자연어 처리 및 텍스트 마이닝의 중요한 과제 중 하나이다. 특히 추출해야할 요소가 한 단어가 아닌 여러 단어로 구성된 경우 추출 과정에서 고려되어야할 부분이 크게 증가한다. 또한 추출 대상이 되는 요소의 유형 또한 여러 가지인데, 감정 분석 분야를 예로 들면 화자, 객체, 속성 등 여러 유형의 요소에 대한 분석이 필요하며, 비교 마이닝 분야를 예로 들면 비교 주체, 비교 상대, 비교 술어 등의 요소에 대한 분석이 필요하다. 본 논문에서는 각각 여러 단어로 구성될 수 있는 여러 유형의 요소를 동시에 추출하는 방법을 제안한다. 제안 방법은 구현이 매우 간단하다는 장점을 가지는데, 필요한 과정은 형태소 부착과 변환 기반 학습(transformation-based learning) 두 가지이며, 파싱 혹은 청킹 같은 별도의 전처리 과정도 거치지 않는다. 평가를 위해 제안 방법을 적용하여 비교 마이닝을 수행하였는데, 비교 문장으로부터 각자 여러 단어로 구성될 수 있는 세 가지 유형의 비교 요소를 자동 추출하였으며, 실험 결과 정확도 84.33%의 우수한 성능을 산출하였다.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.5
• /
• pp.859-865
• /
• 2023

In a situation where service providers are increasingly focusing on content development due to the intense competition in the OTT market, interactive content that encourages active participation from viewers is garnering significant attention. In response to this trend, research on interactive content is being conducted more actively. This study aims to analyze interactive content through text mining techniques, with a specific focus on online unstructured data. The analysis includes deriving the characteristics of keywords according to their weight, examining the relationship between OTT platforms and interactive content, and tracking changes in the trends of interactive content based on objective data. To conduct this analysis, detailed techniques such as 'Word Cloud', 'Relationship Analysis', and 'Keyword Trend' are used, and the study also aims to derive meaningful implications from these analyses.