• The Journal of the Convergence on Culture Technology
• /
• v.6 no.4
• /
• pp.715-720
• /
• 2020

In Big data analysis, text data is mostly unstructured and large-capacity, so analysis was difficult because analysis techniques were not established. Therefore, this study was conducted for the possibility of commercialization through verification of usefulness and problems when applying the big data word cloud technique, one of the text data analysis techniques. In this paper, the limitations and problems of this technique are derived through visualization analysis of the "President UN Speech" using the R program word cloud technique. In addition, by proposing an improved model to solve this problem, an efficient method for practical application of the word cloud technique is proposed.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.5
• /
• pp.49-56
• /
• 2010

In this paper, we implement a Hadoop based cluster for cloud computing and evaluate the performance of this cluster based on application characteristics by executing RandomTextWriter, WordCount, and PI applications. A RandomTextWriter creates given amount of random words and stores them in the HDFS(Hadoop Distributed File System). A WordCount reads an input file and determines the frequency of a given word per block unit. PI application induces PI value using the Monte Carlo law. During simulation, we investigate the effect of data block size and the number of replications on the execution time of applications. Through simulation, we have confirmed that the execution time of RandomTextWriter was proportional to the number of replications. However, the execution time of WordCount and PI were not affected by the number of replications. Moreover, the execution time of WordCount was optimum when the block size was 64~256MB. Therefore, these results show that the performance of cloud computing system can be enhanced by using a scheduling scheme that considers application's characteristics.

• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.172-176
• /
• 2010

본 논문에서는 위키피디아의 '틀(temp late)'을 기조로 하여 작성된 온톨로지인 OntoCloud의 신뢰도를 보장하고 공유 및 재사용을 가능하게 하기 위하여 또 다른 어휘집합체인 워드넷(WordNet)과의 매핑을 한다. 온톨로지 매핑 기술은 온톨로지 개발 기술의 한 방법으로, 서로 비슷한 도메인을 대상으로 이미 구축되어진 서로 다른 다수의 온롤로지를 연결시킴으로서 하나의 풍부한 정보를 가지고 있는 연결망을 구축하는 방법이다. 본 논문에서는 OntoCloud와 워드넷을 두개의 온톨로지로 정의하고 각 온톨로지의 개념에 대한 정의문 비교 방법을 통해서 두개의 온톨로지에 존재하는 유사한 개념을 연결한다. 이렇게 매핑된 정보들은 OntoCloud 개념을 워드넷 어휘로 연결함으로써 개념에 대한 직관적인 이해를 돕고, 워드넷에 연결된 다른 시소러스 (예: SUMO, CoreNet 등)와 간접적으로 연결할 수 있는 틀을 마련한다. 또한 온톨로지의 상하위 계층정보를 자동으로 보강하는 등의 OntoCloud 유지보수에 활용될 수 있다. 본 논문의 실험에서는 두개의 서로 다른 온톨로지의 정의문에 사용된 어휘의 겹침 정도로 두개의 개념의 유사성을 판별하는 방법을 보인다. 본 논문에서 제시한 방법으로 약 73%의 개념 매핑에 성공하였으나, 추후 매핑 프로세스의 전처리 과정(약자 처리 및 복합명사 대응 모듈)을 추가하고 온톨로지의 구조적 특성을 활용하여 유사 개념 자동 매핑 기술을 향상시키고자 한다.

• International Journal of Advanced Culture Technology
• /
• v.12 no.2
• /
• pp.221-226
• /
• 2024

This study used text mining, a big data analysis technique, to explore XR trends in South Korea. For this research, I utilized a big data platform called BigKinds. I collected data focusing on the keyword 'XR', spanning approximately 14 years from 2010 to 2024. The gathered data underwent a cleansing process and was analyzed in three ways: keyword trend analysis, relational analysis, and word cloud. The analysis identified the emergence and most active discussion periods of XR, with XR devices and manufacturers emerging as key keywords.

• Journal of the Korea Fashion and Costume Design Association
• /
• v.20 no.3
• /
• pp.49-62
• /
• 2018

The purpose of this study is to examine women's street fashion based on Instagram by word cloud analysis. This study is divided into items, silhouettes, colors, materials, patterns, and images that appear in women's street fashion. The results of this study are as follows: First, women's fashion-oriented Instagram accounts have a maximum of 8.6 million followers, with 16 blogs have more than one million users. As for the fashion-oriented Instagram visitors, many were their 10s-20s and photography was the key issue. Second, it was found that the casual image, which is the basis of street fashion, romantic, elegance, active sportive image, and sexy images appeared as unique images, and mixed with each other. Third, we compared the fashion characteristics of the top blogs 'fashionnova', 'fashionclimaxx2', and 'fashion.selection'. The blog 'fashionnova', utilizes sexy images and various dresses, and dresses were the characteristic points. The blog 'fashionclimaxx2' features casual images and modern office looks. The blog 'fashoin.selection' has fashion characteristics of both 'fashionnova' and 'fashionclimaxx2'.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2024.01a
• /
• pp.351-354
• /
• 2024

최근 온라인 학습의 비중이 증가함에 따라 온라인 학습 서비스의 일부인 온라인 상담 부분도 비례하여 증가하고 있으며, 많은 상담량으로 인해 상담 서비스의 품질이 저하되고 답변의 속도, 효율성도 감소하는 문제가 발생한다. 국내 교육기관에서는 서비스 개선과 사용자 맞춤형서비스를 제공하기 위해 다양한 연구를 진행하고 있으며 민원을 처리하는 챗봇 등 자동 답변 서비스 도입을 추진하고 있다. 챗봇 및 자동 답변 서비스는 서비스 제공자 입장에서 저예산으로 단순한 질문에 대하여 신속하고 효율적인 서비스를 제공할 수 있으며 서비스 이용자는 즉각적인 답변과 유사한 답변 예시를 확인함으로 질문을 빠르게 해결할 수 있는 장점이 있다. 국가 공공기관에서 제공하는 학습 서비스는 단순하고 반복적인 문의가 많고 정형적인 질의응답이 주로 등록이 되고 있다. 자동 답변 서비스는 이런 문제점을 해결할 수 있는 대안이 된다. 서비스 이용자가 등록한 문의를 기반으로 학습한 답변 서비스는 담당자의 반복된 업무처리 경감과 사용자의 답변감소, 일관된 답변처리로 서비스 품질개선에 큰 영향을 줄 수 있다. 본 연구에서는 사용자의 질문에 효율적인 답변 및 민원 처리 서비스를 제공할 수 있는 방법을 제시하며, 관리자의 업무능력 향상과 효율성을 위해 기간별 키워드 빈도수를 계산하여 Word cloud를 생성하여 제공함으로써 사용자들에게 일정 기간 내 빈도수가 높은 키워드 관련 공지 및 안내를 할 수 있도록 한다.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.4
• /
• pp.745-750
• /
• 2021

In Big data visualization analysis of unstructured text data, raw data is mostly large-capacity, and analysis techniques cannot be applied without cleansing it unstructured. Therefore, from the collected raw data, unnecessary data is removed through the first heuristic cleansing process and Stopwords are removed through the second machine cleansing process. Then, the frequency of the vocabulary is calculated, visualized using the word cloud technique, and key issues are extracted and informationalized, and the results are analyzed. In this study, we propose a new Stopword cleansing technique using an external Stopword set (DB) in Python word cloud, and derive the problems and effectiveness of this technique through practical case analysis. And, through this verification result, the utility of the practical application of word cloud analysis applying the proposed cleansing technique is presented.

• The Korean Journal of Applied Statistics
• /
• v.26 no.6
• /
• pp.999-1007
• /
• 2013

This research shows several types of moving pictures from the data: 1) the word cloud of Korean texts, 2) the heat map of n ${\times}$ p matrices, 3) the moving image of p ${\times}$ p scatterplot matrix, 4) the local projective display of k clusters (Huh and Lee, 2012). Moving pictures may reveal the hidden information and beauty of the datasets and ignite the curiosity of information consumers. Video files are attached.

• Journal of Korea Multimedia Society
• /
• v.22 no.9
• /
• pp.1091-1107
• /
• 2019

The purpose of this study is to technology impact assessment uncertainties and influences of factors for the coexistence technology in MR and to derive the ripple effect of the target technology in many different application fields. This survey is to evaluate the impact of new technologies on economy, society, culture, ethics and environment in advance and to reflect the results in policy research. As a result, we analyzed the positive and negative impacts predicted by the coexistence technology in MR in edutainment field by word cloud analysis. The purpose of these study is to strengthen the intrinsic intent of technology assessment on the edutainment fields to strengthen positive impacts and minimize adverse impacts by identifying the various factors affecting society when the coexistence technology in MR was commercialized as well as by evaluating the positive and negative impacts from a more balanced view.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.751-776
• /
• 2022

Purpose: The purpose of this paper is to present implications by analyzing research trends on CSR, CSV and ESG by text analysis and visual analysis(Comprehensive/ Fields / Years-based) which are big data analyses, by collecting data based on previous studies on CSR, CSV and ESG. Methods: For the collection of analysis data, deep learning was used in the integrated search on the Academic Research Information Service (www.riss.kr) to search for "CSR", "CSV" and "ESG" as search terms, and the Korean abstracts and keyword were scrapped out of the extracted paper and they are organize into EXCEL. For the final step, CSR 2,847 papers, CSV 395 papers, ESG 555 papers derived were analyzed using the Rx64 4.0.2 program and Rstudio using text mining, one of the big data analysis techniques, and Word Cloud for visualization. Results: The results of this study are as follows; CSR, CSV, and ESG studies showed that research slowed down somewhat before 2010, but research increased rapidly until recently in 2019. Research have been found to be heavily researched in the fields of social science, art and physical education, and engineering. As a result of the study, there were many keyword of 'corporate', 'social', and 'responsibility', which were similar in the word cloud analysis. Looking at the frequent keyword and word cloud analysis by field and year, overall keyword were derived similar to all keyword by year. However, some differences appeared in each field. Conclusion: Government support and expert support for CSR, CSV and ESG should be activated, and researches on technology-based strategies are needed. In the future, it is necessary to take various approaches to them. If researches are conducted in consideration of the environment or energy, it is judged that bigger implications can be presented.