• Annual Conference on Human and Language Technology
• /
• 2010.10a
• /
• pp.179-182
• /
• 2010

트위터, 페이스북 등의 소설 네트워크가 이슈가 되는 사건에 의견을 표시하는 수단으로 많이 활용되고 있다. 본 논문에서는 이슈 키워드 추출 및 트위터와 유투브에 기반한 실시간 검색 시스템을 구현한다. 본 시스템에서는 가장 최근 신문 기사들의 제목과 스니핏을 이용하여 이슈가 되는 키워드를 실시간으로 추출하여 사용자들에게 보여주고 트위터와 유투브 OpenAPI를 이용하여 추출된 키워드에 대한 컨텐츠들을 실시간으로 사용자들에게 보여준다, 본 시스템을 통해서 이슈가 되는 사건에 대한 실시간 반응을 찾을 수 있다.

• Journal of Digital Convergence
• /
• v.14 no.12
• /
• pp.237-243
• /
• 2016

Since realtime search keywords of portal sites are arranged in descending order by instant increasing rates of search numbers, they easily show issues increasing in interests for a short time. But they have the limits extracted different results by portal sites and not shown issues by a period. Thus, to find key issues from the whole realtime search keywords for certain period, and to show results of summarizing them and analyzing differences, is significant in providing the basis of understanding issues more practically and in maintaining consistency of them. This paper analyzes differences of week key issues extracted from week analysis of realtime search keywords provided by two typical portal sites. The results of experiments show that the portal group means of realtime search keywords by the independent t-test and the survival functions of realtime search keywords by the survival analysis are statistically significant differences.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.7 no.4
• /
• pp.299-314
• /
• 2017

Technological advances in media have expanded users' consciousness. At the same time, users have changed from passive into active voice by interacting media. The emergence of mobile made different structures and contents compared to the past. Especially, Korean culture of mobile converted original media channels to contents in a category. Plus, the usage structure of internet of this time converges in massive portal sites. It is because that the structure has aspect of emitting through remediation in the sites. Also, Korean massive portal sites have provided specific service named 'real-time issues'. This is not only the unique way of offering information that exists in Korea but also high usability of getting issues. We therefore considered the meaning of durability of real-time issues in the view of journalism, compared original media channels. Then, this paper identified the user attributes for acquisition of information following ways using informal and formal data from Korean massive portal sites named 'Daum' and 'Naver'.

• Journal of Digital Convergence
• /
• v.13 no.8
• /
• pp.253-260
• /
• 2015

Because mass of activity records of individuals and organizations are accumulated in the digital space and amount of information is also increasing exponentially, the most urgent requirements of users is the tool for 'efficient' acquisition of 'useful' information. This paper try digital convergence to combine a domain specific technology with real time issue detection and grouping based on Web media. To derive core functionalities, we collect and analyze user requirements of national defense issue detection services. By utilizing linguistic resources specialized on national defence area and discovering features for measuring issue importance, we try to seek differentiation domain specific issue detection method. Finally we compare our detection results based on the development outputs of prototype.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1096-1097
• /
• 2013

최근 Twitter를 비롯한 소셜 네트워크 서비스의 급속한 확산으로 인해, 많은 수의 SNS 메시지가 실시간으로 생성되고 있다. 이러한 SNS 상의 모든 글을 읽어보는 것은 현실적으로 불가능하며, 여러 포탈 사이트에서 제공되는 실시간 검색어 순위만으로는 상세 내용을 직관적으로 파악하기 어렵다. 따라서, 이러한 SNS상의 글을 실시간으로 분석하여 최신의 트렌드를 찾고 이와 연관된 내용을 분류 및 요약할 수 있다면, 사용자에게 유용한 최신 정보를 생성하여 제공할 수 있다. 본 논문에서는 Tweet 들을 분석하여 얻은 트렌드 키워드를 기반으로 관련된 Tweet 들을 주제 별로 분류한 후, 각 주제 별로 세부 내용을 요약해서 제공하는 기법을 제안한다. 제안하는 기법은 실시간으로 생성되는 Tweet 내에서 최근 화제가 된 트렌드 및 연관 키워드를 추출해낸다. 그 후, 해당 키워드가 출현한 Tweet 내에서 핵심 키워드를 찾고, 이를 기반으로 Tweet 들을 각각의 주제별로 분류하고 각 주제를 '이슈'로 정의한다. 마지막으로, 특정한 이슈에 해당되는 Tweet들을 분석하여 각 이슈 별로 키워드 리스트 및 단문 형식으로 요약된 줄거리를 생성한다. 제안된 기법을 바탕으로 프로토타입 시스템을 구현하고, 다양한 실험을 통하여 이슈 검출 기법의 유용성 면에서 성능을 평가한다.

• Journal of Digital Convergence
• /
• v.17 no.12
• /
• pp.255-260
• /
• 2019

Real-time search keywords are not only limited to search keywords that are rapidly increasing interest in real-time, but also have a limitation that they are difficult to determine the sustainability as there is a difference in ranking between portal sites. Estimating sustainability for real-time search keywords is significant in terms of overcoming these limitations and providing some predictability. In particular, long-term search keywords that last for more than a month are of high value as long-lasting social issues. Therefore, in this paper, we analyze the interest based on the ranking of the real-time search keywords and the duration based on sustained weeks, days and hours of real-time search keywords by each portal site and the integrated portal site, and then estimating sustainability based on high level of interest and duration, and present a method to derive real-time search issues with high long-term sustainability.

• Journal of Digital Convergence
• /
• v.13 no.12
• /
• pp.161-169
• /
• 2015

Realtime search words of typical portal sites appear every few seconds in descending order by search frequency in order to show issues increasing rapidly in interest. However, the characteristics of realtime search words reordering within too short a time cause problems that they go over the key issues of the day. This paper proposes a method for deriving a key issue through association analysis of realtime search words. The proposed method first makes scores of realtime search words depending on the ranking and the relative interest, and derives the top 10 search words through descriptive statistics for groups. Then, it extracts association rules depending on 'support' and 'confidence', and chooses the key issue based on the results as a graph visualizing them. The results of experiments show that the key issue through association rules is more meaningful than the first realtime search word.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.556-578
• /
• 2020

There are many different researches about how to analyze issues based on real-time news streams. But, there are few researches which analyze issues hierarchically from news articles and even a previous research of hierarchical issue analysis make clustering speed slower as the increment of news articles. In this paper, we propose a hierarchical and incremental clustering for semi real-time issue analysis on news articles. We trained siamese neural network based weighted cosine similarity model, applied this model to k-means algorithm which is used to make word clusters and converted news articles to document vectors by using these word clusters. Finally, we initialized an issue cluster tree from document vectors, updated this tree whenever news articles happen, and analyzed issues in semi real-time. Through the experiment and evaluation, we showed that up to about 0.26 performance has been improved in terms of NMI. Also, in terms of speed of incremental clustering, we also showed about 10 times faster than before.

• Annual Conference on Human and Language Technology
• /
• 2018.10a
• /
• pp.132-137
• /
• 2018

뉴스 기반의 실시간 이슈 분석을 위해서는 실시간으로 생성되는 다중 뉴스 기사 집합을 입력으로 받아 점증적으로 군집화 하고, 각 군집별 정보를 자동으로 요약하는 기술이 필요하다. 기존에는 정적인 데이터 기반의 군집화와 요약 각각에 대한 연구는 활발히 진행되고 있지만, 실시간으로 입력되는 대량의 데이터를 위한 점증적인 군집화와 요약에 대한 연구는 매우 부족하다. 따라서 본 논문에서는 실시간으로 입력되는 대량의 뉴스 기사 집합을 분석하기 위한 점증적이고 계층적인 뉴스 군집화 및 다중 문서 요약 방법을 제안한다. 평가를 위해서 2016년 10월, 11월 두 달간의 실제 데이터를 사용 하였으며, 전문 교육을 받은 연구원들이 Precision at k 기반의 정성평가를 진행하였다. 그 결과, 자동으로 생성된 12개의 군집에서 군집 성능은 평균 66% (상위계층 $l_1$: 82%, 하위계층 $l_2$: 43%), 요약 성능은 평균 92%를 얻었다.

• Journal of Digital Convergence
• /
• v.16 no.12
• /
• pp.335-342
• /
• 2018

The search service, which is a core service of the portal site, presents search queries that are rapidly increasing among the inputted search queries based on the highest instantaneous search frequency, so it is difficult to immediately notify a search query having a high degree of interest for a certain period. Therefore, it is necessary to overcome the above problems and to provide more intelligent information retrieval service by bringing improved analysis results on the change of the search queries. In this paper, we present the criteria for measuring the interest, continuity, and attention of real-time search queries. In addition, according to the criteria, we measure and summarize changes in real-time search queries in hours, days, weeks, and months over a period of time to assess the issues that are of high interest, long-lasting issues of interest, and issues that need attention in the future.