• Health Policy and Management
• /
• v.32 no.3
• /
• pp.334-339
• /
• 2022

The digital response is an excellent infection prevention and control measure to minimize person-to-person contact when a respiratory infectious disease is rapidly spreading. However, few studies have explored the reasons for the development and utilization of these technologies. Here, we analyze documents by the Korean government, existing research, and news articles to provide a qualitative review of the digital response, and new concepts explored by Korea during coronavirus disease 2019, to apply them for the next infectious disease outbreak.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1630-1648
• /
• 2021

Owing to the unprecedented COVID-19 pandemic, the pharmaceutical industry has attracted considerable attention, spurred by the widespread expectation of vaccine development. In this study, we collect relevant topics from news articles related to COVID-19 and explore their links with two South Korean pharmaceutical indices, the Drug and Medicine index of the Korea Composite Stock Price Index (KOSPI) and the Korean Securities Dealers Automated Quotations (KOSDAQ) Pharmaceutical index. We use generalized Dirichlet-multinomial regression (g-DMR) to reveal the dynamic topic distributions over metadata of index values. The results of our analysis, obtained using g-DMR, reveal that a greater focus on specific news topics has a significant relationship with fluctuations in the indices. We also provide practical and theoretical implications based on this analysis.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.8
• /
• pp.91-101
• /
• 2021

This paper intends to draw implications for preparing for Post-Corona in the health field and policy fields as the global pandemic is experienced due to COVID-19. The purpose of this study is to analyze the news and trends of media companies through temporal analysis of the three infectious diseases, SARS-CoV, MERS-CoV, and SARS-CoV-2 (COVID-19), in which the domestic infectious disease preventive system was active throughout the first year of the outbreak. To this end, by using the news analysis program of the Korea Press Foundation 'Big Kinds', the number of news articles per year was digitized based on the period when each infectious disease had an impact on Korea, and major trends were implemented and analyzed in a word cloud. As a result of the analysis, the number of articles related to infectious diseases peaked when the World Health Organization (WHO) declared a warning and (suspicious) confirmed cases occurred. According to keyword and word cloud analysis, 'infectious disease outbreak and major epidemic areas', 'prevention authorities', and 'disease information and confirmed patient information' were found to be the main common features, and differences were derived from the three infectious diseases. In addition, the current status of the infodemic was identified by performing word cloud analysis on information in uncertainty. The results of this study are significant in that they were able to derive the roles of the health authorities and the media that should be preceded in the event of a new disease epidemic through previously experienced infectious diseases, and areas to be rearranged.

• The KIPS Transactions:PartB
• /
• v.12B no.6 s.102
• /
• pp.691-696
• /
• 2005

In this paper, we present a pilot system that tn compress a Korean sentence automatically using knowledge extracted from news articles and their headlines. A sot of compressed sentences can be presented as an abstraction of a document. As a compressed sentence is of headline-style, it could be easily displayed on small devices, such as mobile phones and other handhold devices. Our compressing system has shown to be promising through a preliminary experiment.

• Journal of Computing Science and Engineering
• /
• v.10 no.4
• /
• pp.128-136
• /
• 2016

It is impossible for any human being to analyze the more than 500 million tweets that are generated per day. Lexical ambiguities on Twitter make it difficult to retrieve the desired data and relevant topics. Most of the solutions for the word sense disambiguation problem rely on knowledge base systems. Unfortunately, it is expensive and time-consuming to manually create a knowledge base system, resulting in a knowledge acquisition bottleneck. To solve the knowledge-acquisition bottleneck, a topic signature is used to disambiguate words. In this paper, we evaluate the effectiveness of various features of newspapers on the topic signature extraction for word sense discrimination in tweets. Based on our results, topic signatures obtained from a snippet feature exhibit higher accuracy in discriminating company names than those from the article body. We conclude that topic signatures extracted from news articles improve the accuracy of word sense discrimination in the automated analysis of tweets.

• Korean journal of communication and information
• /
• v.43
• /
• pp.209-246
• /
• 2008

This research is a comparative analysis of article titles in the beginning period of Korean newspapers. The Independent, The Korea Daily News and The Dong-A Ilbo were chosen for this research because each was the representative newspaper of 1890s, 1900s and $1920s{\sim}1930s$ respectively. In result, The Independent's article titles had been appeared on nearly 2 years after its first issue. Before the appearance of titles, The Independent had divided articles only with section names. In 1900s, The Korean Daily News's article titles was longer than those of The independent. And in 1910, the titles of The Korean Daily News had been placed on separated line to divide articles clearly. But during these period, typographical development of titles was not shown and the width of title was remained in one column. This means, the function of title in these periods was not to represent the value of article but only to divide the articles. In 1920s, The Dong-A Ilbo had used big size types and multi-column edit and those changes enabled newspaper to introduce the concept of layout. During the decade of 1930s, The Dong-A Ilbo's titles had occupied more space on newspaper than earlier period. This could be explained from the perspective of sensationalism of commercial newspaper and a tendency of putting more weight on titles. On the dimension of expression, proportions of subjective titles in The Independent, The Korea Daily News were 44.4% and 28.3% each, but the subjective titles of The Dong-A Ilbo in 1920's were only 4.2%. This decrease can be explained by the settlement of objective journalism in Korean newspapers during $1920s{\sim}1930s$.

• Korean journal of communication and information
• /
• v.57
• /
• pp.160-180
• /
• 2012

This research points out how the major newspapers and the Local newspaper try to report the issue of development in Incheon Free Economic Zone differently and observe how the press has played a role in a process. It is seen that the type of story-leading has been followed by properly traditional one as usual and reflected the recent trends well in both. The perspectives of ChosunIlbo to look at the regional issue is taken in the situation of a middle clear attitude but KyeonginIlbo is faithful to make the position of the monitor. In other words, a Metropolitan newspaper often deals with the regional issues in a more passive posture, while a Local daily newspaper tries to report the same issue in a more positive and active form. This kind of attitude upon news composition reflects the quality of the news, which is a standard of actual newspaper articles. The ChosunIlbo focuses on the political issues more while, KyeonginIlbo emphasizes on the cultural similarities. And they trace the economic importance, human interest but less to the structural figures.

• Korean journal of communication and information
• /
• v.76
• /
• pp.151-182
• /
• 2016

The right to be forgotten (RTBF) has been a population notion to address privacy issues associated with the digitalization of information and the dissemination of such information over the global digital network. In May 2014, the European Court of Justice (ECJ) laid down a landmark RTBF decision to grant individuals the right to be de-listed from search results. ECJ's RTBF decision sparked an increased interest in RTBF in South Korea. Academic and non-academic commentators have provided a mistaken or outstretched interpretation of RTBF in claiming that removal of news articles should be read into RTBF in Korean law. Moreover, the Press Arbitration Commission of Korea (PAC) has proposed revising the Press Arbitration Act (PAA) to allow the alleged victims of news reporting to request the deletion of news stories. This article examines the notion of RTBF from its origin to the latest development abroad and also critically explores Korean laws regulation freedom of expression to evaluate if Korea needs the proposed PAA revision.

• Journal of KIISE
• /
• v.44 no.7
• /
• pp.742-747
• /
• 2017

In this paper, we propose a novel approach to improve the performance of the Convolutional Neural Network(CNN) word embedding model on top of word2vec with the result of performing like doc2vec in conducting a document classification task. The Word Piece Model(WPM) is empirically proven to outperform other tokenization methods such as the phrase unit, a part-of-speech tagger with substantial experimental evidence (classification rate: 79.5%). Further, we conducted an experiment to classify ten categories of news articles written in Korean by feeding words and document vectors generated by an application of WPM to the baseline and the proposed model. From the results of the experiment, we report the model we proposed showed a higher classification rate (89.88%) than its counterpart model (86.89%), achieving a 22.80% improvement. Throughout this research, it is demonstrated that applying doc2vec in the document classification task yields more effective results because doc2vec generates similar document vector representation for documents belonging to the same category.

• The Journal of Sustainable Design and Educational Environment Research
• /
• v.19 no.2
• /
• pp.11-20
• /
• 2020

The goal of this study was to investigate the implementation and related issues of the school space innovation issued by key Korean mass media using text mining. To accomplish this goal, this study collected 519 news articles associated with the school space innovation issued by 54 Korean mass media companies. Based on this data, this study performed the frequency analysis and network analysis regarding the keywords. Based on the findings, the characteristics of school space innovation are summarized as follows: First, school space innovation has progressed in response to future education. Second, users are actively participating in school space innovation. Third, experts are supporting the innovation of school space by establishing a cooperative system. Fourth, the community is actively considering the innovation of school space. Fifth, the main projects of the Ministry of Education and the Provincial Offices of Education are actively conducted in a mix of top-down and bottom-up approaches. The findings of this study will contribute to providing a clear direction for contemporary school space innovation and implications for future research agenda and implementation.