• Journal of KIISE
• /
• v.42 no.5
• /
• pp.664-670
• /
• 2015

With the rapid progression of the Internet and smartphones, YouTube has grown significantly as a social media sharing site and has become popular all around the world. As users share videos through YouTube, social data are created and users look for video recommendations related to their interests. In this paper, we extract users' social category based on their social relationship and social category classification list using YouTube data. We propose the YouTube recommendation algorithm using the extracted users' social category for more accurate and meaningful recommendations. We show experiment results of its validation.

• Journal of the Korean Society for Library and Information Science
• /
• v.48 no.4
• /
• pp.91-113
• /
• 2014

Although social metadata has strengths in creating amount of user-contributed resource descriptions, its function is limited because of its non-systematic characteristics. This research proposed an alternative approach to semantic organization of social metadata. It analyzed the semantics of tags created in LibraryThing in order to provide bibliographic categories for describing information resources. Social information Architecture is adopted in generating the bibliographic categories so that social metadata framework can be constructed. This framework can provide the conceptual foundations for semantically organizing social metadata and is expected to be applied to the existing approaches to automatically organize social metadata.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.5
• /
• pp.563-569
• /
• 2012

The studies of opinion mining or sentiment analysis have been the focus with social web proliferation. Sentiment analysis requires sentiment resources to decide its polarity. In the existing sentiment analysis, they have been built resources designed with intensity of sentiment polarity and decided polarity of opinion using the ones. In this paper, I will present sentiment categories for not only polarity of opinion but also the basis of positive/negative opinion. I will define psychological emotions to primary sentiments for the reasonable classification. And I will extract the informations of sentiment from social web texts for the actual distribution of sentiments in social web. Re-classifying primary sentiments based on extracted sentiment information, I will organize sentiment categories for the social web. In this paper, I will present 23 categories of sentiment by using proposed method.

• Journal of Internet Computing and Services
• /
• v.15 no.5
• /
• pp.73-82
• /
• 2014

SNS becomes a recent issue, and many researches in various kinds of field are being done by taking advantage of it. Especially, there are many researches existed on the system that finds user's interest and makes recommendation based on multiple social data generated on the SNS. User's interest is not only revealed from the user's writing but also from the user's relationship with friends. This study proposes a recommendation method that extracts user's interest by using social relationship and its categorization applies it to the recommendation. In this way, it can recommend user's interest with category based on the writings by the user and furthermore it can apply the user's relationship with his/her friends for more accurate recommendation. In addition, if necessary, the recommendation can be made by extracting any interest shared between the user and specific friends. Through experiments, we show that our method using social category can produce satisfactory result.

• Annual Conference of KIPS
• /
• 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 Society for e-Business Studies
• /
• v.14 no.2
• /
• pp.41-56
• /
• 2009

The purpose of this paper is to present a statistical model that can predict the rapid shift of users' attention by analyzing the lifecycle patterns of news in a social news aggregation service. Internet news service sites have a distinct characteristic in a sense that users' attention change very quickly in a short period of time. In this research, we propose a regression model for each news category which can model the decay pattern of users' attention and the content promotion policy of a social news aggregator is proven to be a major source of the rapid growth in the popularity of news. The proposed model is expected to be useful for evaluation of the social news aggregation service provider's content promotion policy that attempts to maximize users' attention as well as the diversity of news contents.

• Annual Conference of KIPS
• /
• 2009.04a
• /
• pp.391-394
• /
• 2009

정보의 양이 폭발적으로 증가함에 따라 웹 사용자가 원하는 적합한 데이터를 찾아내는 것은 매우 어렵다. 이는 웹 사용자마다 서로 다른 검색의도와 질의의 모호성에 의한 것으로, 이와 같은 검색의 어려움을 해결하기 위해 많은 연구들이 수행되어 왔다. 질의 로그는 검색자의 검색 의도가 내포되어 있는 중요한 자료이다. 따라서 웹 사용자별 질의 로그 패턴을 분석하여 유사한 질의를 사용하는 웹 사용자들을 클러스터링 하여 검색에 적용한다면 좀 더 유용한 정보를 획득할 수 있다. 즉, 특정 카테고리와 연관된 질의를 자주 사용하는 웹 사용자들은 해당 분야에 관심이 많을 것이며, 또한 다른 카테고리에 관심이 높은 사람보다 상호간에 소셜지수가 높게 나타날 것이다. 특정 주제에 대해 검색을 할 경우 해당 분야에 관심이 높은 웹 사용자들의 질의 및 클릭한 URL 정보를 상속받을 수 있다면 찾고자 하는 정보에 보다 빨리 접근할 수 있다. 따라서 본 연구는 질의패턴 분석을 통해 카테고리별로 관심도가 높은 웹 사용자들을 클러스터링 한 후 해당 카테고리에 대한 정보 검색시 이들이 사용한 질의와 클릭한 URL 정보를 웹 사용자들에게 제공해줌으로써 정보검색의 편의성을 향상시키기 위한 방안을 제안한다.

• Journal of Korean Society for Geospatial Information Science
• /
• v.23 no.2
• /
• pp.89-96
• /
• 2015

Location-based social media data have high potential to be used in various area such as big data, location based services and so on. In this study, we applied a series of analysis methodology to figure out how the important keywords in location-based social media are spatially distributed by analyzing text information. For this purpose, we collected tweet data with geo-tag in Gangnam district and its environs in Seoul for a month of August 2013. From this tweet data, principle keywords are extracted. Among these, keywords of three categories such as food, entertainment and work and study are selected and classified by category. The spatial clustering is conducted to the tweet data which contains keywords in each category. Clusters of each category are compared with buildings and benchmark POIs in the same position. As a result of comparison, clusters of food category showed high consistency with commercial areas of large scale. Clusters of entertainment category corresponded with theaters and sports complex. Clusters of work and study showed high consistency with areas where private institutes and office buildings are concentrated.

• TTA Journal
• /
• s.111
• /
• pp.45-52
• /
• 2007

웹2.0 개념이 소개된 이후로 웹 2.0의 실체에 대한 논란이 끊임없이 제기되어 왔다. 하지만 웹2.0의 실체는 있다. 웹2.0은 사용자 중심의 콘텐츠와 상호작용, 커뮤니케이션 능력의 확장을 구현하는 새로운 서비스들로 구성되어 있으며, 그것은 하나의 사회적 현상이 되어 문화에까지 영향을 미치고 있다. 또한 최근에는 기업 내부의 업무에도 영향을 미치는 단계로까지 발전하고 있다. 기술적인 측면에서 볼때 웹2.0은 소셜 컴퓨팅이 인터넷 애플리케이션으로 구현된 것이다. 본 고는 그러한 소셜 컴퓨팅의 카테고리와 그에 해당하는 정의 및 관련 웹2.0 서비스들을 살펴보고, 국내 웹 비즈니스 현황에 대해 알아보고자 한다. 이를 통해 웹2.0의 여러 서비스들의 가치 및 국내 웹 비즈니스가 처한 현실에 대한 이해를 돕고자 한다.

• Smart Media Journal
• /
• v.5 no.3
• /
• pp.54-61
• /
• 2016

According to many smart devices are development, SNS(Social Network Service) users are getting higher that is possible for real-time communicating, information sharing without limitations in distance and space. Nowadays, SNS users that based on communication and relationships, are getting uses SNS for information sharing. In this paper, we used the SNS posts for users to extract the category and information provider, how to following of recommend method. Particularly, this paper focuses on classifying the words in the text of the posts and measures the frequency using Inception-v3 model, which is one of the machine learning technique -CNN(Convolutional Neural Network) we classified image word. By classifying the category of a word in a text and image, that based on DMOZ to build the information provider DB. Comparing user categories classified in categories and posts from information provider DB. If the category is matched by measuring the degree of similarity to the information providers is classified in the category, we suggest that how to recommend method of the most similar information providers account.