• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.118-118
• /
• 2019

현재 홍수예보는 정형데이터인 유량 및 수위 등을 활용하여 이뤄지고 있다. 하지만 실제 사람들이 체감하는 홍수에 대한 위험도는 홍수예보 발령과는 달라 홍수예보가 이뤄지지 않은 지역에서 인명사고가 발생하기도 한다. 이는 수위 측정이 이뤄지지 않는 소규모 하천이나 사람들의 유동성이 큰 도심지역에서 빈번하게 발생한다. 이를 보완하기 위해서는 사람들의 체감 정도 및 인구의 유동성을 고려한 비정형데이터를 활용해야 한다. 특히 소셜 네트워크 서비스(Social Network Commuinty, SNS)를 사용하는 사람들이 많아지면서 기존에 사용되어 왔던 정형데이터 센서 이외의 데이터를 제공한다. 또한 개개인이 작성하는 글은 실시간으로 활용이 가능하여 인구의 유동성 및 시 공간적 데이터를 얻기에 유용하여 활용성이 매우 높은 비정형데이터이다. 따라서 본 연구에서는 SNS 데이터를 추출하고 이를 분석하여 2018년에 발생했던 강우사상과의 패턴을 비교하여 홍수예보에서의 활용성을 분석하였다. 홍수와 관련한 키워드를 중심으로 시 공간적 정보 및 추출이 가능한 웹 크롤러(Web Crawler) 프로그램을 작성하였으며 이를 토대로 데이터를 수집하였다. 수집한 데이터와 실제 홍수사상을 비교 분석을 한 결과 강우량 및 수위와 해당 지역에 대한 데이터의 양이 유사한 패턴을 보인 것으로 확인되었다. 실시간으로 데이터를 수집하고 이를 분석하여 리드타임을 충분히 확보한다면 홍수예측에 활용 가능할 것이라 생각된다. 본 연구는 한국건설기술연구원 19주요-대4-시드사업인 '커뮤니티 빅데이터 패턴 해석을 통한 수난(水難) 발생 및 규모 예측 기술 개발(20190126-001) '로 수행되었습니다.

• Journal of Digital Convergence
• /
• v.12 no.6
• /
• pp.277-287
• /
• 2014

In LBSNS(Location-based Social Network Service), users can share locations and communicate with others by using check-in data. The check-in data consists of POI name, category, coordinate and address of locations, nickname of users, evaluating grade of locations, related article/photo/video, and etc. If you analyze the check-in data from the location-based social network service in accordance with your situation, you can provide various customized services. Therefore, In this paper, we develop a location recommendation system based on LBSNS that can utilize the check-in data efficiently. This system analyzes the location category of the check-in data, determines the weighted value of it, and finds out the similarity between users by using the Pearson correlation coefficient. Also, it obtains the preference score of recommended locations by using the collaborated filtering algorithm and then, finds out the distance score by applying the Euclidean's algorithm to the recommended locations and the current users' locations. Finally, it recommends appropriate locations by applying the weighted value to the preference score and the distance score. In addition, this paper approved excellence of the proposed system throughout the experiment using real data.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.32 no.3
• /
• pp.247-264
• /
• 2021

This study aims to create a deep learning-based classification model to classify suicide tendency by suicide corpus constructed for the present study. Also, to analyze suicide factors, the study classified suicide tendency corpus into detailed topics by using topic modeling, an analysis technique that automatically extracts topics. For this purpose, 2,011 documents of the suicide-related corpus collected from social media naver knowledge iN were directly annotated into suicide-tendency documents or non-suicide-tendency documents based on suicide prevention education manual issued by the Central Suicide Prevention Center, and we also conducted the deep learning model(LSTM, BERT, ELECTRA) performance evaluation based on the classification model, using annotated corpus data. In addition, one of the topic modeling techniques, LDA identified suicide factors by classifying thematic literature, and co-word analysis and visualization were conducted to analyze the factors in-depth.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.546-558
• /
• 2021

This study focused on analyzing the contents of social big data produced in the online space, dealing with issues related to food in the community in the context of COVID-19. First, this study analyzed food-related issues that spread through regional websites and online community(cafes) after social distancing was implemented due to COVID-19. Next, this study analyzed the contents of food-related issues that spread through media news, SNS, and portals. As a result, there were more food-related posts on the homepages of other regions compared to the metropolitan areas such as Seoul and Gyeonggi, but in the case of online communities, there were more food-related issues in online communities registered in Seoul and Gyeonggi regions. Food-related keywords in regional online communities mainly contained content related to the local economy. In the media articles, SNS, and search portal issues, content that can be discussed in the consumption process of local community food-related policies, information, and products mainly appeared. Based on the results of the study, it was found that there is no specialized information sharing system for each community, that online communities can contribute to providing food information applicable to reality, and that it is possible to verify the performance of regional food policies through social media.

• Journal of Internet Computing and Services
• /
• v.16 no.6
• /
• pp.23-30
• /
• 2015

As BigData is issued, many applications that operate based on the results of data analysis have been developed, typically applications are products recommend service of e-commerce application service system, search service on the search engine service and friend list recommend system of social network service. In this paper, we suggests a decision frequent pattern tree that is combined the origin frequent pattern tree that is mining similar pattern to appear in the data set of the existing data mining techniques and decision tree based on the theory of computer science. The decision frequent pattern tree algorithm improves about problem of frequent pattern tree that have to make some a lot's pattern so it is to hard to analyze about data. We also proposes to model for a Mapredue framework that is a programming model to help to operate in distributed environment.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2015.10a
• /
• pp.1581-1584
• /
• 2015

최근 소셜 네트워크 서비스상의 데이터를 실시간으로 분석하여 의미있는 정보를 찾아내기 위한 연구가 활발하게 진행되고 있다. 특히, 스마트폰과 같은 스마트 디바이스를 이용하는 많은 사용자들이 실시간으로 발생하는 이벤트를 소셜 네트워크상에 게재하고 서로 공유하면서, 대중들이 관심을 가지는 토픽의 경우 굉장히 빠르게 확산되는 경향을 보이고 있다. 본 논문에서는 이러한 SNS의 특성을 토대로 트위터상의 트윗을 분석하여 여러 분야의 토픽들을 카테고리별로 분류하고, 카테고리별 트렌드를 추출하여 실시간으로 시각화하는 기법을 제안한다. 이를 위해, 트위터를 기반으로 SVM 분류 알고리즘과 Twitter-LDA를 통하여 트윗을 분야별로 분류하고, 각각의 트렌드를 이루는 대표적인 키워드를 선출하여 이를 기반으로 실시간 트렌드를 추출한다. 제안하는 기법의 성능을 평가하기 위해, 분류 특징 선택의 신뢰도를 측정한다.

• The Journal of the Korea Contents Association
• /
• v.14 no.4
• /
• pp.97-109
• /
• 2014

Social media is a general term for online services by which users share opinions, perspectives, and experiences. It supports interactions between users in sharing contents on it and weak ties among them play an important role in the process. This exploratory study attempts to identify crucial factors of establishing weak ties between social media users in the perspective of social network theory and uncertainty reduction theory. We collected data through diary study and in-depth interview and analyzed it following grounded theory approach. As a result, social media users more actively interacted each other or shared contents based on weak ties, compared to strong ties. In addition, similarity, self-disclosure, and relevance appeared to facilitate establishment of weak ties, by reducing psychological distance between social media users and perceived uncertainty of them.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.533-534
• /
• 2021

최근 소셜 네트워크 서비스(SNS)를 통한 건강기능식품 과대광고 적발이 증가하면서 SNS를 통해 브랜드를 선택함에 있어 신뢰도가 소비자에게 중요한 요소가 된다. 본 논문에서는 인스타그램의 해시태그를 이용해 게시글을 크롤링 하여 수집된 게시물 데이터를 가공 및 분석한다. 불용어 사전을 구축해 불용어를 제거해준 뒤 브랜드 추출을 진행하고, 건강기능식품 브랜드 5개에 대한 게시글 데이터를 수집한다. 5개 브랜드의 신뢰도 측정을 위해 게시글, 해시태그, 계정명을 분석기준으로 삼아 라벨링 처리를 한다. 라벨링 된 열을 통해 절대적 수치로 점수를 부여하여 백분율로 점수를 표현한다. 신뢰도 점수와 더불어 브랜드의 고객 참여도 건수를 같이 명시해 준다.

• Journal of the Korean Applied Science and Technology
• /
• v.39 no.6
• /
• pp.853-863
• /
• 2022

In order to revitalize start-ups in the beauty field, this study attempted to derive characteristic patterns of changes in demand and differences in emotions and meaning for 'beauty start-ups' by dividing the period by year from 2019 to 2021 based on exploratory data analysis (EDA). Most of the search terms related to the keyword "beauty start-up" showed more interest in institutions or certificates that can learn beauty skills than professional start-up education, which still does not recognize the importance of start-up education, and as an alternative, it is necessary to develop customized start-up education programs for each major. We establish hypotheses through exploratory data analysis and verify hypotheses by combining traditional corroborative data analysis (CDA). There has never been an exploratory data analysis method for beauty startups, and rather than mentioning the need for formal start-up education, analyzing changes in interest in beauty startups and the requirements of prospective start-ups with exploratory data will help develop customized start-up programs.

• KIPS Transactions on Software and Data Engineering
• /
• v.9 no.11
• /
• pp.367-376
• /
• 2020

The fourth industrial revolution will greatly contribute to the entry of objects into an intelligent society through technologies such as big data and an artificial intelligence. Through the revolution, we were able to understand human behavior and awareness, and through the use of an artificial intelligence, we established ourselves as a key tool in various fields such as medicine and science. However, the fourth industrial revolution has a negative side with a positive future. In this study, an analysis was conducted using text mining techniques based on unstructured big data collected through social media. We wanted to look at keywords related to the fourth industrial revolution by year (2016, 2017 and 2018) and understand the meaning of each keyword. In addition, we understood how the keywords related to the Fourth Industrial Revolution changed with the change of the year and wanted to use R to conduct a Keyword Analysis to identify the recognition flow closely related to the Fourth Industrial Revolution through the keyword flow associated with the Fourth Industrial Revolution. Finally, people's perceptions of the fourth industrial revolution were identified by looking at the positive and negative feelings related to the fourth industrial revolution by year. The analysis showed that negative opinions were declining year after year, with more positive outlook and future.