• Proceedings of the Korean Society for Emotion and Sensibility Conference
• /
• 2009.05a
• /
• pp.39-42
• /
• 2009

4 세대 모바일폰은 카메라, MP3, 블루투스, DMB, 전자수첩, PC, 웹브라우징의 복합 기능을 가진 제품으로 진화하고 있으며, 이를 위한 사용자의 요구와 경험디자인의 요소를 탐색하고 분석하는 것이 요구된다. 하지만 기존의 사용자 요구의 조사와 경험디자인은 많은 비용과 시간을 투입하고도 기존 요구의 재확인에 머물거나, 제한적이고 예측 가능한 결과만을 도출하는 문제점을 가지고 있어 창의적 디자인 아이디어 도출에는 한계를 가지고 있다. 이는 사용자의 선정과 분석의 방법이 마케팅 중심의 통계적 방법에 기초하고 있으며, 사용자의 선정에 분석의 결과가 좌우되기 때문이다. 본 연구는 창의적 경험디자인의 방법으로서 1% 이미지 추출의 작업과 국내외 커뮤니티 사이트를 중심으로 한 디지털 포켓리서치의 방법을 활용하였나 2차 사용자 조사는 '1% UX 리서치'로 명명한 극단적 사용자 분석의 방법을 개발하고 적용하였으며, 주요 디자인 요구와 암시점은 K-J 매트릭스를 통하여 체계화하였다. 디지털포켓리서치와 1% 사용자의 리서치의 방법론은 근 미래의 사용자 예측과 풍부한 경험디자인의 아이디어를 발상할 수 있다는 측면에서 기존의 방법론 보다 비용과 시간 측면에서 효율적으로 활용할 수 있었다.

• Annual Conference of KIPS
• /
• 2010.11a
• /
• pp.531-534
• /
• 2010

웹 2.0의 적극적인 도입에 따라 소셜 네트워크 기반 커뮤니티 사이트에서는 관련된 콘텐츠를 적절하게 추천하는 것은 중요한 문제로 부각되고 있으며 이로 인해 사용자들의 동향 및 이슈 추출 기법이 중요하게 작용하고 있다. 이러기 위해서 지금까지의 연구에서는 콘텐츠에 포함된 키워드 매칭 방법을 이용하고 있으나 사용자들 간의 연결 관계와 키워드의 중요도를 고려하지 못하고 있다. 본 논문에서는 FOAF 기반의 소셜 네트워크와 del.icio.us에서 제공하는 소셜 북마크 데이터를 기초로 소셜네트워크 분석을 보이며 이를 통한 사용자들 사이에서 중요하게 부각되는 핫 이슈를 추출하는 방법을 제안한다. 본 논문에서 제안하는 핫 이슈 추출 방법을 활용하면 사용자들의 관심 분야 동향파악을 효율적으로 수행할 수 있으며 이를 통해 맞춤형 마케팅 및 콘텐츠 추천이 가능해 진다.

• Journal of Convergence for Information Technology
• /
• v.11 no.10
• /
• pp.1-9
• /
• 2021

Although interest in the metaverse increases due to the pandemic, the understanding of the metaverse interest factor, which is an essential element for the sustainability of any metaverse platform, is lacking. This study aims to reveal the interest factors of metaverse services by analyzing user community discourse. We collected user community discourses from and applied LDA to extract topics. Further, we categorize the factors into growth and verifiable indicators, various levels of interaction, self-expression and freedom, and connection with the real world. The content planning direction of the game-based metaverse of utilization was derived. This study is meaningful in that it analyzes the interest factors of the metaverse based on the empirical evidence of user discourse data.

• Journal of Korean Library and Information Science Society
• /
• v.54 no.3
• /
• pp.33-55
• /
• 2023

There has been research to understand users' information behaviors using book circulation data of public libraries. In this study, we examined the subject areas of books simultaneously borrowed by users of public libraries and aimed to identify the relationships among the subject areas. To accomplish this, we utilized the Korean Decimal Classification codes of 984,790 loaned books in 2019 to transform the lists of concurrently borrowed books, totaling 22,443,699 records, by the same users on the same day, into vectors using the ITEM2VEC technique. Next, we extracted ten highly related classification codes for each classification code, utilizing a total of 522 classification codes to create a network. We identified 15 communities within this network and examined the characteristics of each community. Among the 15 communities, those consisting of two or more main classes allowed us to identify meaningful thematic associations. This study, grounded in users' book usage behaviors, has suggested the topics of books that could be borrowed together. The findings offer valuable insights for library collection development and placement, recommending related subject materials, and revising classification systems.

• Journal of KIISE
• /
• v.43 no.10
• /
• pp.1085-1093
• /
• 2016

Community-based Question Answering system is a system which provides answers for each question from the documents uploaded on web communities. In order to enhance the capacity of question analysis, former methods have developed specific rules suitable for a target region or have applied machine learning to partial processes. However, these methods incur an excessive cost for expanding fields or lead to cases in which system is overfitted for a specific field. This paper proposes a multiple machine learning method which automates the overall process by adapting appropriate machine learning in each procedure for efficient processing of community-based Question Answering system. This system can be divided into question analysis part and answer selection part. The question analysis part consists of the question focus extractor, which analyzes the focused phrases in questions and uses conditional random fields, and the question type classifier, which classifies topics of questions and uses support vector machine. In the answer selection part, the we trains weights that are used by the similarity estimation models through an artificial neural network. Also these are a number of cases in which the results of morphological analysis are not reliable for the data uploaded on web communities. Therefore, we suggest a method that minimizes the impact of morphological analysis by using character features in the stage of question analysis. The proposed system outperforms the former system by showing a Mean Average Precision criteria of 0.765 and R-Precision criteria of 0.872.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.133-137
• /
• 2023

In this paper, we developed a 'comprehensive pet management application' that combines pet AI diagnosis, animal hospital search, smart household accounts, and community functions. The application can solve the inconvenience of users who have to use multiple functions as separate applications, and can easily use pet AI diagnosis services through photos, provides animal hospital information using crawling, finds nearby animal hospitals, and supports smart households that can scan receipts using OCR text extraction techniques. By using this application, information necessary for raising pets such as health and consumption details of pets can be managed in one system.

• Annual Conference of KIPS
• /
• 2014.11a
• /
• pp.845-848
• /
• 2014

블로그는 인터넷에서 개인의 정보나 의견을 표출하고 커뮤니티를 형성하는데 사용되는 중요한 수단이나, 광고 유치, 페이지 순위 올리기, 쓰레기 데이터 생성 등 다양한 목적을 가진 스팸블로그가 생성되어 악용되기도 한다. 본 연구에서는 이러한 문제를 해결하기 위해 웹 문서에서 나타나는 특징들을 이용한 스팸 탐지 기법을 제안한다. 먼저 블로그 본문의 길이, 태그의 비율, 태그 수, 이미지 수, 랭크의 수 등 하나의 웹 문서에서 추출할 수 있는 특징을 기반으로 각 문서에 대한 특징 벡터를 생성하고 기계학습을 통해 모델을 생성하여 스팸 블로그를 판별한다. 제안 방법의 성능 평가를 위해 블로그 포스트 데이터를 사용하여 제안방법과 기존의 스팸 분류 연구를 비교 실험을 진행하였다. Bayesian 필터링 기법을 사용하는 기존연구와 비교 실험 결과, 제안방법이 더 좋은 정확도를 가지면서 특징 추출 속도 및 메모리 사용 효율성을 보였다.

• Korean journal of communication and information
• /
• v.81
• /
• pp.9-39
• /
• 2017

Online communities have become playgrounds for enjoyment and political public spheres as well as have been vitalized by participation of diverse users, which shows that users of online communities experience participatory democracy and new subjects who project the politic of everyday life eventually. The purpose of the study is to examine that how phenomenon from above have been revealed in the academic discourses and seek the ways for development of the theory and methodology of community media research. To do this, I analyze that features and tendencies of academic discourses which have historically been accumulated through applying method of meta-analysis into topics, methods, and issues in the precedence studies. Data is centered on Journals of the Korean Society for Journalism and communication Studies, Korean Association for Broadcasting and Telecommunication studies, Korean Association for Communication and Information studies, and the Cybercommunication Academic Society. The reason why I choose these journals is that they have a long history of the publication compared to other journals, thus, I can collect various related articles. Total of 53 Samples are selected after input keywords '공동체' and 'Community'. This study makes a contribution by offering the preliminary data in order to seek the ways for revitalization of local communities and for the future theories and methodologies of community media through researching on precedence studies having piled from 2001 when the first article about community media was published to November 2016.

• Spatial Information Research
• /
• v.20 no.2
• /
• pp.129-136
• /
• 2012

Recently international organizations such as ISO/TC211, OGC, INSPIRE (Infrastructure for Spatial Information in Europe) make an effort to share geospatial data using semantic web technologies. In addition, smart phone and social networking services enable community-based opportunities for participants to share issues of a social phenomenon based on geographic area, and many researchers try to find a method of extracting issues from that. However, serviceable spatial ontologies are still insufficient at application level, and studies of spatial information extraction from SNS were focused on user's location finding or geocoding by text mining. Therefore, a study of extracting spatial phenomenon from social media information and converting it into geosemantic knowledge is very usable. In this paper, we propose a framework for extracting keywords from micro-blog, one of the social media services, finding their relationships using data mining technique, and converting it into spatiotemopral knowledge. The result of this study could be used for implementing a related system as a procedure and ontology model for constructing geoseem antic issue. And from this, it is expected to improve the effectiveness of finding, publishing and analysing spatial issues.

• 한국노년학
• /
• v.41 no.2
• /
• pp.271-284
• /
• 2021

This study was conducted to derive factors that affect the satisfaction of home visiting health care services and to develop effective community care models by using the results of Seoul's outreach service which is the basis for Korean community care. The population of the study was the elderly aged 65 and 70 who participated in the Seoul's outreach community services 3rd stage (July 2017 - June 2018) and 4th stage (July 2018 to June 2019). 2,200 people were extracted by the proportional allocation method and home visit interviews were conducted on them. Subjects were divided into sub-groups based on chronic disease prevalence, and logistic regression was conducted to derive factors that affect the satisfaction of home visiting health care services. The results demonstrated that the elderly without chronic diseases were more satisfied when they received health education and counseling services, the elderly with one chronic disease were more satisfied when they received Community resource-linked services. In the case of elderly people with two or more chronic diseases, the service satisfaction level is increased when health condition assessment and Community resource-linked services are provided. Regardless of whether or not they have chronic diseases, service delivery time was a factor that increased satisfaction in home visiting health care. And the degree of explanation understanding was a factor that increased satisfaction for both single and complex chronic patients. Home Visiting health care services based on the community is a key component of the ongoing community care. In order to increase the sustainability and effectiveness of community care in the future, Community-oriented health care services based on the degree of chronic diseases of the elderly should be provided. In order to provide more effective services, however, it is necessary (1) to establish a linkage system to share health information of the subject held by the National Health Insurance Service to local governments and (2) to provide capacity-building education for visiting nurses to improve the quality of home visiting health care services. It is hoped that this study will be us ed as bas ic data for the successful settlement of community care.