• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.397-400
• /
• 2022

본 연구에서는 소셜 네트워크 서비스(Social Network Service, SNS) 데이터로부터 약물 부작용 게시글을 추출하기 위한 순환 신경망(Recurrent Neural Network, RNN) 기반 분류 모델을 제안한다. 먼저, 처방 빈도가 높으며 게시글을 많이 확보할 수 있는 케토프로펜 약물에 대하여 국내 최대 소셜 네트워크 플랫폼인 네이버 블로그와 카페의 게시글(2005 년~2020 년)을 확보하고 최종 3,828 건을 분석하였다. 결과적으로 케토프로펜에 대한 3 종(약물, 부작용, 불용어)의 렉시콘을 정의하였으며 이를 기반으로 Bi-LSTM 분류모델 기준 87%의 정확도를 얻었다. 본 연구에서 제안하는 모델은 SNS 데이터가 약물 부작용 정보 획득을 위한 기존 (전자의무기록, 자발적 약물 부작용 보고 시스템 등) 자료원에 대한 보완적 정보원이 되며, 개발된 Bi-LSTM 분류모델을 통해 약물 부작용 게시글 추출의 편리성을 제공할 것으로 기대된다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.166-171
• /
• 2020

Big data processing technology that can store and analyze data and obtain new knowledge has been adjusted for importance in many fields of the society. Big data is emerging as an important problem in the field of information and communication technology, but the mind of continuous technology is rising. the R, a tool that can analyze big data, is a language and environment that enables information analysis of statistical bases. In this paper, we use this to analyze the Bible data. We analyze the four Gospels of the New Testament in the Bible. We collect the Bible data and perform filtering for analysis. The R is used to investigate the frequency of what text is distributed and analyze the Bible through social network analysis, in which words from a sentence are paired and analyzed between words for accurate data analysis.

• 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.

• The Journal of the Korea Contents Association
• /
• v.20 no.3
• /
• pp.515-526
• /
• 2020

Digital healthcare is a combined area of medical field and IT and various information on digital healthcare is provided in social media. This study aims to find the research trend of digital healthcare by collecting and analyzing data related to digital healthcare through the social media. The data were collected from Naver and Daum's news and blogs from January 2008 to June 2019. Major keywords with high frequency were extracted and visualized with wordcloud and network analysis was used to analyze the relationship between major keywords. Research combining medical field and IT from 2008 to 2001, various convergence research based on medical field and IT from 2012 to 2015, convergence research that applied the 4th industrial revolution technologies such as big data, blockchain and AI were actively conducted from 2016 to June 2019.

• Journal of Digital Convergence
• /
• v.14 no.10
• /
• pp.137-145
• /
• 2016

The explosive growth of social networking services based on smart devices popularize these relationships and activities online in accordance with the far larger impact of this on the real life offline, the interest and importance for the online activity is increasing. In this study, factors affecting the SNS activity are defined by object, user, influence direction, influence distance and proposed a method to measure organic terms in effect between the SNS users. Influence Direction and Influence Strength (or Distance) are elaborated by using the existing influence measurement element such as structured data - the number of friends, the difference between the number of contacts - and the new influence measurement element such as unstructured data - gap between the former time and the latter time, preference and type of response behavior - that occur in social network service. In addition, the system for collecting and analysing data for measuring influence from social network service and the process model on the method for measuring influence is tested by using sample data on Facebook and explained the implementation probability.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.22 no.3
• /
• pp.505-514
• /
• 2012

Because people usually establish their online social network based on their offline relationship, the social networks (i.e., the graph of friendship relationships) are often used to share contents. Mobile devices let it easier in these days, but it also increases the privacy risk such as access control of shared data and relationship exposure to untrusted server. To control the access on encrypted data and protect relationship from the server, M. Atallah et al. proposed a hop-based scheme in 2009. Their scheme assumed a distributed environment such as p2p, and each user in it shares encrypted data on their social network. On the other hand, it is very inefficient to keep their relationship private, so we propose an improved scheme. In this paper, among encrypted contents and relationships, some authenticated users can only access the data in distributed way. For this, we adopt 'circular-secure symmetric encryption' first. Proposed scheme guarantees the improved security and efficiency compared to the previous work.

• Journal of Digital Convergence
• /
• v.18 no.10
• /
• pp.195-206
• /
• 2020

This study aims to analyze the effect of consumer characteristics such as consumer innovativeness on using popular social media in Korea. Social media usage is estimated by probit and multinomial probit model with user characteristics using Korea media panel data of 2019. According to the analysis, users with hedonoc innovativeness are likely to use social media, while users with cognitive innovativeness are not likely to use it. Regarding individual social media usage, functional innovativeness increases the probability of using Kakaostory, and hedonic innovativeness increases the likelihood of using Instagram. However, cognitive innovativeness decreases the probability of using Kakaosotry and Naver Band. This study gives insights into finding out specific social media for marketing certain products with innovativeness. In future research, it may be worthwhile to analyze under the assumption that a social media user is using several social media simultaneously.

• Journal of Digital Contents Society
• /
• v.11 no.4
• /
• pp.571-578
• /
• 2010

Recently, many social networking services using mobile devices are spread. Also, many studies based on location and time are increasing. However, existing studies have been difficult to resolve queries by place, time, and events. In the paper, we propose time and space modeling method for social services. We propose Human Activity Graph and Quad Relation Factors through time, place, event, and social activity of users, and we design the database scheme for data collect and analysis.

• Proceedings of the Korea Information Processing Society Conference
• /
• 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.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1294-1297
• /
• 2011

최근, Flickr, YouTube 와 같은 사용자 참여형 미디어 공유 및 검색 사이트가 폭발적으로 증가하면서, 이를 멀티미디어 정보 검색 서비스에 효과적으로 활용하기 위한 다양한 연구들이 시도되고 있다. 특히, 이미지에 할당되어 있는 태그를 이용하여 이미지를 효과적으로 검색하기 위한 연구가 활발히 진행 중이다. 그러나 사용자들에 의해 제공되는 소셜 이미지들은 매우 다양한 범위와 주제를 가지고 있기 때문에, 소셜 이미지들의 분류 및 태그 할당을 위한 트레이닝 집합의 획득이 쉽지 않다는 한계점을 가지고 있다. 본 논문에서는 데이터 군집화를 위한 클러스터링 알고리즘들 중 K-Means, K-Medoids, Affinity Propagation 을 활용하여 소셜 이미지 집합으로부터 트레이닝 집합을 획득하기 위한 방법들을 살펴 본다. 또한, 각 알고리즘으로부터 획득한 트레이닝 집합을 이용하여 소셜 이미지를 분류한 결과를 비교 분석한다.