• 월간 기계설비
• /
• s.232
• /
• pp.34-43
• /
• 2009

• 월간 기계설비
• /
• s.237
• /
• pp.53-54
• /
• 2010

• 보건세계
• /
• v.53 no.11 s.603
• /
• pp.16-19
• /
• 2006

• 대학교육
• /
• s.186
• /
• pp.46-50
• /
• 2014

• 월간 기계설비
• /
• s.238
• /
• pp.17-24
• /
• 2010

• 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.

• Korean journal of communication and information
• /
• v.26
• /
• pp.157-208
• /
• 2004

This study explored how television news constructed an issue of the building of a nuclear waste facility on Wido, an issue which displayed a social conflict in the latter half of the year 2003. To do this, this study conducted frame analysis on KBS and MBC main news including national and local ones, broadcasted from 11 July, 2003 to 10 December, 2003. It was found that television news tended to stress violent protests against site designation and social disorder rather than the causes of a conflict and its solutions. Therefore, news reporting excluded fundamental reasons of conflict such as the governmental decision-making process of site designation, geological suitability, safety issue and nuclear energy policy, emphasizing the confrontation and clash between pro and con groups of site designation. This indicates that television news defines an issue of the building of a nuclear waste facility as the local conflict between groups, the police and demonstrators, or neighbors who approve and protest the site designation, not as the national issue of nuclear policy.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1167-1173
• /
• 2015

The development of information and communication technology like SNS, blogs, and bulletin boards, was provided a variety of places where you can express your thoughts and comments and allowing Big Data to grow, many people reveal the opinion of the social issues in SNS such as Twitter. In this study, we would like to pre-built sentimental dictionary about social issues and conduct a sentimental analysis with structured dictionary, to gather opinions on social issues that are created on twitter. The data that I used is "bikini", "nakkomsu" including tweet. As the result of analysis, precision is 61% and F1- score is 74%. This study expect to suggest the standard of dictionary construction allowing you to classify positive/negative opinion on specific social issues.

• Journal of The Korean Association of Information Education
• /
• v.25 no.4
• /
• pp.633-640
• /
• 2021

Education related issues are social problems in which various groups and situations are intricately linked to each other. It is difficult to find issues by analyzing social phenomena related to education. Korean based text analysis can be analyzed in a quantitative. With the development of text analysis techniques, research results have been recently achieved, and it can be fully utilized to derive educational issues from text data in Korean. In this study, petition articles in the field of childcare/education were collected on the online-board of the Blue House National Petition website, and text analysis was used to derive issues in the education world. The analysis derived 6 topics through Latent Dirichlet Allocation(LDA) among topic modeling techniques. The association rules of major keywords were analyzed and visualized as graphs. In addition to deriving educational issues through the existing questionnaire, it can provide implications for future research directions and policies in that issues can be sufficiently discovered through text-based analysis methods.

• ICROS
• /
• v.15 no.4
• /
• pp.28-37
• /
• 2009

여기에서는 그린 IT와 유비쿼터스 정보화 기술의 주요이슈들을 분석하였다. 그린 IT의 주요 이슈는 어떻게 하면 $CO_2$ 배출량을 줄일 것인가에 있고, 유비쿼터스 정보화에서는 언제 어디서나와 같은 유비쿼터스 개념을 담은 웰빙 서비스 기술들을 어떻게 구현하느냐에 있다. 따라서 본 고에서는 이러한 웰빙 사회를 위한 u-그린 도시 전략을 소개하고자 한다.